Reasoning


Recent Readings for Reasoning of Foundation Models (since 2022) (Index of Posts):

No. Read Date Title and Information We Read @
1 2025, Apr, 18 Inference test time scaling law 2025-S4
2 2025, Apr, 11 More on LLM based agents 2025-S4
3 2025, Mar, 12 Extra readings - Agent Guardrailing 2025-S4
4 2025, Feb, 5 advanced LLM - Math reasoning 2025-S4
5 2025, Feb, 3 advanced LLM - for code reasoning 2025-S4


Here is a detailed list of posts!



[1]: Inference test time scaling law


Scaling

In this session, our readings cover:

Required Readings:

What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models

  • [Submitted on 31 Mar 2025]
  • Qiyuan Zhang, Fuyuan Lyu, Zexu Sun, Lei Wang, Weixu Zhang, Zhihan Guo, Yufei Wang, Irwin King, Xue Liu, Chen Ma
  • As enthusiasm for scaling computation (data and parameters) in the pretraining era gradually diminished, test-time scaling (TTS), also referred to as ``test-time computing’’ has emerged as a prominent research focus. Recent studies demonstrate that TTS can further elicit the problem-solving capabilities of large language models (LLMs), enabling significant breakthroughs not only in specialized reasoning tasks, such as mathematics and coding, but also in general tasks like open-ended Q&A. However, despite the explosion of recent efforts in this area, there remains an urgent need for a comprehensive survey offering a systemic understanding. To fill this gap, we propose a unified, multidimensional framework structured along four core dimensions of TTS research: what to scale, how to scale, where to scale, and how well to scale. Building upon this taxonomy, we conduct an extensive review of methods, application scenarios, and assessment aspects, and present an organized decomposition that highlights the unique functional roles of individual techniques within the broader TTS landscape. From this analysis, we distill the major developmental trajectories of TTS to date and offer hands-on guidelines for practical deployment. Furthermore, we identify several open challenges and offer insights into promising future directions, including further scaling, clarifying the functional essence of techniques, generalizing to more tasks, and more attributions.

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

  • [Submitted on 6 Aug 2024]
  • URL
  • Charlie Snell, Jaehoon Lee, Kelvin Xu, Aviral Kumar
  • Enabling LLMs to improve their outputs by using more test-time computation is a critical step towards building generally self-improving agents that can operate on open-ended natural language. In this paper, we study the scaling of inference-time computation in LLMs, with a focus on answering the question: if an LLM is allowed to use a fixed but non-trivial amount of inference-time compute, how much can it improve its performance on a challenging prompt? Answering this question has implications not only on the achievable performance of LLMs, but also on the future of LLM pretraining and how one should tradeoff inference-time and pre-training compute. Despite its importance, little research attempted to understand the scaling behaviors of various test-time inference methods. Moreover, current work largely provides negative results for a number of these strategies. In this work, we analyze two primary mechanisms to scale test-time computation: (1) searching against dense, process-based verifier reward models; and (2) updating the model’s distribution over a response adaptively, given the prompt at test time. We find that in both cases, the effectiveness of different approaches to scaling test-time compute critically varies depending on the difficulty of the prompt. This observation motivates applying a “compute-optimal” scaling strategy, which acts to most effectively allocate test-time compute adaptively per prompt. Using this compute-optimal strategy, we can improve the efficiency of test-time compute scaling by more than 4x compared to a best-of-N baseline. Additionally, in a FLOPs-matched evaluation, we find that on problems where a smaller base model attains somewhat non-trivial success rates, test-time compute can be used to outperform a 14x larger model.

s1: Simple test-time scaling

  • https://arxiv.org/abs/2501.19393
  • Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, Tatsunori Hashimoto
  • Test-time scaling is a promising new approach to language modeling that uses extra test-time compute to improve performance. Recently, OpenAI’s o1 model showed this capability but did not publicly share its methodology, leading to many replication efforts. We seek the simplest approach to achieve test-time scaling and strong reasoning performance. First, we curate a small dataset s1K of 1,000 questions paired with reasoning traces relying on three criteria we validate through ablations: difficulty, diversity, and quality. Second, we develop budget forcing to control test-time compute by forcefully terminating the model’s thinking process or lengthening it by appending “Wait” multiple times to the model’s generation when it tries to end. This can lead the model to double-check its answer, often fixing incorrect reasoning steps. After supervised finetuning the Qwen2.5-32B-Instruct language model on s1K and equipping it with budget forcing, our model s1-32B exceeds o1-preview on competition math questions by up to 27% (MATH and AIME24). Further, scaling s1-32B with budget forcing allows extrapolating beyond its performance without test-time intervention: from 50% to 57% on AIME24. Our model, data, and code are open-source at this https URL

More Readings:

Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models

  • [Submitted on 1 Aug 2024 (v1), last revised 14 Oct 2024 (this version, v2)]
  • Yangzhen Wu, Zhiqing Sun, Shanda Li, Sean Welleck, Yiming Yang
  • While the scaling laws of large language models (LLMs) training have been extensively studied, optimal inference configurations of LLMs remain underexplored. We study inference scaling laws and compute-optimal inference, focusing on the trade-offs between model sizes and generating additional tokens with different inference strategies. As a first step towards understanding and designing compute-optimal inference methods, we studied cost-performance trade-offs for inference strategies such as greedy search, majority voting, best-of-n, weighted voting, and two different tree search algorithms, using different model sizes and compute budgets. Our findings indicate smaller models (e.g., Llemma-7B) can outperform larger models given the same computation budgets, and that smaller models paired with advanced inference algorithms yield Pareto-optimal cost-performance trade-offs. For instance, the Llemma-7B model, equipped with our novel tree search algorithm, consistently outperforms Llemma-34B with standard majority voting on the MATH benchmark across all FLOPs budgets. We hope these findings contribute to a broader understanding of inference scaling laws for LLMs.

[2]: More on LLM based agents


Scaling

In this session, our readings cover:

Required Readings:

Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

  • [Submitted on 31 Mar 2025]
  • Bang Liu, Xinfeng Li, Jiayi Zhang, Jinlin Wang, Tanjin He, Sirui Hong, Hongzhang Liu, Shaokun Zhang, Kaitao Song, Kunlun Zhu, Yuheng Cheng, Suyuchen Wang, Xiaoqiang Wang, Yuyu Luo, Haibo Jin, Peiyan Zhang, Ollie Liu, Jiaqi Chen, Huan Zhang, Zhaoyang Yu, Haochen Shi, Boyan Li, Dekun Wu, Fengwei Teng, Xiaojun Jia, Jiawei Xu, Jinyu Xiang, Yizhang Lin, Tianming Liu, Tongliang Liu, Yu Su, Huan Sun, Glen Berseth, Jianyun Nie, Ian Foster, Logan Ward, Qingyun Wu, Yu Gu, Mingchen Zhuge, Xiangru Tang, Haohan Wang, Jiaxuan You, Chi Wang, Jian Pei, Qiang Yang, Xiaoliang Qi, Chenglin Wu
  • The advent of large language models (LLMs) has catalyzed a transformative shift in artificial intelligence, paving the way for advanced intelligent agents capable of sophisticated reasoning, robust perception, and versatile action across diverse domains. As these agents increasingly drive AI research and practical applications, their design, evaluation, and continuous improvement present intricate, multifaceted challenges. This survey provides a comprehensive overview, framing intelligent agents within a modular, brain-inspired architecture that integrates principles from cognitive science, neuroscience, and computational research. We structure our exploration into four interconnected parts. First, we delve into the modular foundation of intelligent agents, systematically mapping their cognitive, perceptual, and operational modules onto analogous human brain functionalities, and elucidating core components such as memory, world modeling, reward processing, and emotion-like systems. Second, we discuss self-enhancement and adaptive evolution mechanisms, exploring how agents autonomously refine their capabilities, adapt to dynamic environments, and achieve continual learning through automated optimization paradigms, including emerging AutoML and LLM-driven optimization strategies. Third, we examine collaborative and evolutionary multi-agent systems, investigating the collective intelligence emerging from agent interactions, cooperation, and societal structures, highlighting parallels to human social dynamics. Finally, we address the critical imperative of building safe, secure, and beneficial AI systems, emphasizing intrinsic and extrinsic security threats, ethical alignment, robustness, and practical mitigation strategies necessary for trustworthy real-world deployment.

A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning

  • https://arxiv.org/abs/2406.05804
  • [Submitted on 9 Jun 2024 (v1), last revised 30 Nov 2024 (this version, v6)] Xinzhe Li
  • Tool use, planning, and feedback learning are currently three prominent paradigms for developing Large Language Model (LLM)-based agents across various tasks. Although numerous frameworks have been devised for each paradigm, their intricate workflows and inconsistent taxonomy create challenges in understanding and reviewing the frameworks across different paradigms. This survey introduces a unified taxonomy to systematically review and discuss these frameworks. Specifically, 1) the taxonomy defines environments/tasks, common LLM-profiled roles or LMPRs (policy models, evaluators, and dynamic models), and universally applicable workflows found in prior work, and 2) it enables a comparison of key perspectives on the implementations of LMPRs and workflow designs across different agent paradigms and frameworks. 3) Finally, we identify three limitations in existing workflow designs and systematically discuss the future work. Resources have been made publicly available at in our GitHub repository this https URL.
  • Comments: CoLing 2025 Camera Ready (extended to 9 pages)

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

  • [Submitted on 8 Jan 2025]
  • Xinyu Guan, Li Lyna Zhang, Yifei Liu, Ning Shang, Youran Sun, Yi Zhu, Fan Yang, Mao Yang
  • We present rStar-Math to demonstrate that small language models (SLMs) can rival or even surpass the math reasoning capability of OpenAI o1, without distillation from superior models. rStar-Math achieves this by exercising “deep thinking” through Monte Carlo Tree Search (MCTS), where a math policy SLM performs test-time search guided by an SLM-based process reward model. rStar-Math introduces three innovations to tackle the challenges in training the two SLMs: (1) a novel code-augmented CoT data sythesis method, which performs extensive MCTS rollouts to generate step-by-step verified reasoning trajectories used to train the policy SLM; (2) a novel process reward model training method that avoids naïve step-level score annotation, yielding a more effective process preference model (PPM); (3) a self-evolution recipe in which the policy SLM and PPM are built from scratch and iteratively evolved to improve reasoning capabilities. Through 4 rounds of self-evolution with millions of synthesized solutions for 747k math problems, rStar-Math boosts SLMs’ math reasoning to state-of-the-art levels. On the MATH benchmark, it improves Qwen2.5-Math-7B from 58.8% to 90.0% and Phi3-mini-3.8B from 41.4% to 86.4%, surpassing o1-preview by +4.5% and +0.9%. On the USA Math Olympiad (AIME), rStar-Math solves an average of 53.3% (8/15) of problems, ranking among the top 20% the brightest high school math students. Code and data will be available at this https URL.

More Readings:

Agent Laboratory: Using LLM Agents as Research Assistants

  • [Submitted on 8 Jan 2025]
  • Samuel Schmidgall, Yusheng Su, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Jiang Liu, Zicheng Liu, Emad Barsoum
  • Historically, scientific discovery has been a lengthy and costly process, demanding substantial time and resources from initial conception to final results. To accelerate scientific discovery, reduce research costs, and improve research quality, we introduce Agent Laboratory, an autonomous LLM-based framework capable of completing the entire research process. This framework accepts a human-provided research idea and progresses through three stages–literature review, experimentation, and report writing to produce comprehensive research outputs, including a code repository and a research report, while enabling users to provide feedback and guidance at each stage. We deploy Agent Laboratory with various state-of-the-art LLMs and invite multiple researchers to assess its quality by participating in a survey, providing human feedback to guide the research process, and then evaluate the final paper. We found that: (1) Agent Laboratory driven by o1-preview generates the best research outcomes; (2) The generated machine learning code is able to achieve state-of-the-art performance compared to existing methods; (3) Human involvement, providing feedback at each stage, significantly improves the overall quality of research; (4) Agent Laboratory significantly reduces research expenses, achieving an 84% decrease compared to previous autonomous research methods. We hope Agent Laboratory enables researchers to allocate more effort toward creative ideation rather than low-level coding and writing, ultimately accelerating scientific discovery.

Phi-4 Technical Report

  • https://arxiv.org/abs/2412.08905
  • Marah Abdin, Jyoti Aneja, Harkirat Behl, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Michael Harrison, Russell J. Hewett, Mojan Javaheripi, Piero Kauffmann, James R. Lee, Yin Tat Lee, Yuanzhi Li, Weishung Liu, Caio C. T. Mendes, Anh Nguyen, Eric Price, Gustavo de Rosa, Olli Saarikivi, Adil Salim, Shital Shah, Xin Wang, Rachel Ward, Yue Wu, Dingli Yu, Cyril Zhang, Yi Zhang
  • We present phi-4, a 14-billion parameter language model developed with a training recipe that is centrally focused on data quality. Unlike most language models, where pre-training is based primarily on organic data sources such as web content or code, phi-4 strategically incorporates synthetic data throughout the training process. While previous models in the Phi family largely distill the capabilities of a teacher model (specifically GPT-4), phi-4 substantially surpasses its teacher model on STEM-focused QA capabilities, giving evidence that our data-generation and post-training techniques go beyond distillation. Despite minimal changes to the phi-3 architecture, phi-4 achieves strong performance relative to its size – especially on reasoning-focused benchmarks – due to improved data, training curriculum, and innovations in the post-training scheme.

Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling

  • [Submitted on 29 Aug 2024 (v1), last revised 7 Oct 2024 (this version, v2)]
  • https://arxiv.org/abs/2408.16737
  • Hritik Bansal, Arian Hosseini, Rishabh Agarwal, Vinh Q. Tran, Mehran Kazemi
  • Training on high-quality synthetic data from strong language models (LMs) is a common strategy to improve the reasoning performance of LMs. In this work, we revisit whether this strategy is compute-optimal under a fixed inference budget (e.g., FLOPs). To do so, we investigate the trade-offs between generating synthetic data using a stronger but more expensive (SE) model versus a weaker but cheaper (WC) model. We evaluate the generated data across three key metrics: coverage, diversity, and false positive rate, and show that the data from WC models may have higher coverage and diversity, but also exhibit higher false positive rates. We then finetune LMs on data from SE and WC models in different settings: knowledge distillation, self-improvement, and a novel weak-to-strong improvement setup where a weaker LM teaches reasoning to a stronger LM. Our findings reveal that models finetuned on WC-generated data consistently outperform those trained on SE-generated data across multiple benchmarks and multiple choices of WC and SE models. These results challenge the prevailing practice of relying on SE models for synthetic data generation, suggesting that WC may be the compute-optimal approach for training advanced LM reasoners.

Synthetica: Large Scale Synthetic Data for Robot Perception

  • [Submitted on 28 Oct 2024]
  • Ritvik Singh, Jingzhou Liu, Karl Van Wyk, Yu-Wei Chao, Jean-Francois Lafleche, Florian Shkurti, Nathan Ratliff, Ankur Handa
  • Vision-based object detectors are a crucial basis for robotics applications as they provide valuable information about object localisation in the environment. These need to ensure high reliability in different lighting conditions, occlusions, and visual artifacts, all while running in real-time. Collecting and annotating real-world data for these networks is prohibitively time consuming and costly, especially for custom assets, such as industrial objects, making it untenable for generalization to in-the-wild scenarios. To this end, we present Synthetica, a method for large-scale synthetic data generation for training robust state estimators. This paper focuses on the task of object detection, an important problem which can serve as the front-end for most state estimation problems, such as pose estimation. Leveraging data from a photorealistic ray-tracing renderer, we scale up data generation, generating 2.7 million images, to train highly accurate real-time detection transformers. We present a collection of rendering randomization and training-time data augmentation techniques conducive to robust sim-to-real performance for vision tasks. We demonstrate state-of-the-art performance on the task of object detection while having detectors that run at 50-100Hz which is 9 times faster than the prior SOTA. We further demonstrate the usefulness of our training methodology for robotics applications by showcasing a pipeline for use in the real world with custom objects for which there do not exist prior datasets. Our work highlights the importance of scaling synthetic data generation for robust sim-to-real transfer while achieving the fastest real-time inference speeds. Videos and supplementary information can be found at this URL: this https URL.

Small Language Models (SLMs) Can Still Pack a Punch: A survey

  • [Submitted on 3 Jan 2025]
  • Shreyas Subramanian, Vikram Elango, Mecit Gungor
  • As foundation AI models continue to increase in size, an important question arises - is massive scale the only path forward? This survey of about 160 papers presents a family of Small Language Models (SLMs) in the 1 to 8 billion parameter range that demonstrate smaller models can perform as well, or even outperform large models. We explore task agnostic, general purpose SLMs, task-specific SLMs and techniques to create SLMs that can guide the community to build models while balancing performance, efficiency, scalability and cost. Furthermore we define and characterize SLMs’ effective sizes, representing increased capability with respect to LLMs.

[3]: Extra readings - Agent Guardrailing


Safety

In this session, our readings cover:

Required Readings:

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

  • [Submitted on 19 Jun 2024 (v1), last revised 24 Nov 2024 (this version, v3)]
  • Edoardo Debenedetti, Jie Zhang, Mislav Balunović, Luca Beurer-Kellner, Marc Fischer, Florian Tramèr
  • AI agents aim to solve complex tasks by combining text-based reasoning with external tool calls. Unfortunately, AI agents are vulnerable to prompt injection attacks where data returned by external tools hijacks the agent to execute malicious tasks. To measure the adversarial robustness of AI agents, we introduce AgentDojo, an evaluation framework for agents that execute tools over untrusted data. To capture the evolving nature of attacks and defenses, AgentDojo is not a static test suite, but rather an extensible environment for designing and evaluating new agent tasks, defenses, and adaptive attacks. We populate the environment with 97 realistic tasks (e.g., managing an email client, navigating an e-banking website, or making travel bookings), 629 security test cases, and various attack and defense paradigms from the literature. We find that AgentDojo poses a challenge for both attacks and defenses: state-of-the-art LLMs fail at many tasks (even in the absence of attacks), and existing prompt injection attacks break some security properties but not all. We hope that AgentDojo can foster research on new design principles for AI agents that solve common tasks in a reliable and robust manner.. We release the code for AgentDojo at this https URL.

SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model

  • [Submitted on 28 Jan 2025 (v1), last revised 23 Feb 2025 (this version, v2)]
  • Xun Liang, Simin Niu, Zhiyu Li, Sensen Zhang, Hanyu Wang, Feiyu Xiong, Jason Zhaoxin Fan, Bo Tang, Shichao Song, Mengwei Wang, Jiawei Yang
  • The indexing-retrieval-generation paradigm of retrieval-augmented generation (RAG) has been highly successful in solving knowledge-intensive tasks by integrating external knowledge into large language models (LLMs). However, the incorporation of external and unverified knowledge increases the vulnerability of LLMs because attackers can perform attack tasks by manipulating knowledge. In this paper, we introduce a benchmark named SafeRAG designed to evaluate the RAG security. First, we classify attack tasks into silver noise, inter-context conflict, soft ad, and white Denial-of-Service. Next, we construct RAG security evaluation dataset (i.e., SafeRAG dataset) primarily manually for each task. We then utilize the SafeRAG dataset to simulate various attack scenarios that RAG may encounter. Experiments conducted on 14 representative RAG components demonstrate that RAG exhibits significant vulnerability to all attack tasks and even the most apparent attack task can easily bypass existing retrievers, filters, or advanced LLMs, resulting in the degradation of RAG service quality. Code is available at: this https URL.

AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems

  • Chi-Min Chan, Jianxuan Yu, Weize Chen, Chunyang Jiang, Xinyu Liu, Weijie Shi, Zhiyuan Liu, Wei Xue, Yike Guo
  • The rapid advancement of large language models (LLMs) has led to the rise of LLM-based agents. Recent research shows that multi-agent systems (MAS), where each agent plays a specific role, can outperform individual LLMs. However, configuring an MAS for a task remains challenging, with performance only observable post-execution. Inspired by scaling laws in LLM development, we investigate whether MAS performance can be predicted beforehand. We introduce AgentMonitor, a framework that integrates at the agent level to capture inputs and outputs, transforming them into statistics for training a regression model to predict task performance. Additionally, it can further apply real-time corrections to address security risks posed by malicious agents, mitigating negative impacts and enhancing MAS security. Experiments demonstrate that an XGBoost model achieves a Spearman correlation of 0.89 in-domain and 0.58 in more challenging scenarios. Furthermore, using AgentMonitor reduces harmful content by 6.2% and increases helpful content by 1.8% on average, enhancing safety and reliability. Code is available at \url{this https URL}.

More Readings:

Agents for Software Development

  • https://www.phontron.com/slides/neubig24softwareagents.pdf

Identifying the Risks of LM Agents with an LM-Emulated Sandbox

  • Yangjun Ruan, Honghua Dong, Andrew Wang, Silviu Pitis, Yongchao Zhou, Jimmy Ba, Yann Dubois, Chris J. Maddison, Tatsunori Hashimoto
  • Recent advances in Language Model (LM) agents and tool use, exemplified by applications like ChatGPT Plugins, enable a rich set of capabilities but also amplify potential risks - such as leaking private data or causing financial losses. Identifying these risks is labor-intensive, necessitating implementing the tools, setting up the environment for each test scenario manually, and finding risky cases. As tools and agents become more complex, the high cost of testing these agents will make it increasingly difficult to find high-stakes, long-tailed risks. To address these challenges, we introduce ToolEmu: a framework that uses an LM to emulate tool execution and enables the testing of LM agents against a diverse range of tools and scenarios, without manual instantiation. Alongside the emulator, we develop an LM-based automatic safety evaluator that examines agent failures and quantifies associated risks. We test both the tool emulator and evaluator through human evaluation and find that 68.8% of failures identified with ToolEmu would be valid real-world agent failures. Using our curated initial benchmark consisting of 36 high-stakes tools and 144 test cases, we provide a quantitative risk analysis of current LM agents and identify numerous failures with potentially severe outcomes. Notably, even the safest LM agent exhibits such failures 23.9% of the time according to our evaluator, underscoring the need to develop safer LM agents for real-world deployment.

Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models

  • [Submitted on 3 Mar 2025 (v1), last revised 5 Mar 2025 (this version, v2)]
  • Alberto Purpura, Sahil Wadhwa, Jesse Zymet, Akshay Gupta, Andy Luo, Melissa Kazemi Rad, Swapnil Shinde, Mohammad Shahed Sorower
  • The rapid growth of Large Language Models (LLMs) presents significant privacy, security, and ethical concerns. While much research has proposed methods for defending LLM systems against misuse by malicious actors, researchers have recently complemented these efforts with an offensive approach that involves red teaming, i.e., proactively attacking LLMs with the purpose of identifying their vulnerabilities. This paper provides a concise and practical overview of the LLM red teaming literature, structured so as to describe a multi-component system end-to-end. To motivate red teaming we survey the initial safety needs of some high-profile LLMs, and then dive into the different components of a red teaming system as well as software packages for implementing them. We cover various attack methods, strategies for attack-success evaluation, metrics for assessing experiment outcomes, as well as a host of other considerations. Our survey will be useful for any reader who wants to rapidly obtain a grasp of the major red teaming concepts for their own use in practical applications.

Safeguarding Large Language Models: A Survey

  • [Submitted on 3 Jun 2024]
  • Yi Dong, Ronghui Mu, Yanghao Zhang, Siqi Sun, Tianle Zhang, Changshun Wu, Gaojie Jin, Yi Qi, Jinwei Hu, Jie Meng, Saddek Bensalem, Xiaowei Huang
  • In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as “safeguards” or “guardrails”, has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This article provides a systematic literature review on the current status of this critical mechanism. It discusses its major challenges and how it can be enhanced into a comprehensive mechanism dealing with ethical issues in various contexts. First, the paper elucidates the current landscape of safeguarding mechanisms that major LLM service providers and the open-source community employ. This is followed by the techniques to evaluate, analyze, and enhance some (un)desirable properties that a guardrail might want to enforce, such as hallucinations, fairness, privacy, and so on. Based on them, we review techniques to circumvent these controls (i.e., attacks), to defend the attacks, and to reinforce the guardrails. While the techniques mentioned above represent the current status and the active research trends, we also discuss several challenges that cannot be easily dealt with by the methods and present our vision on how to implement a comprehensive guardrail through the full consideration of multi-disciplinary approach, neural-symbolic method, and systems development lifecycle.

[4]: advanced LLM - Math reasoning


Reasoning

In this session, our readings cover:

Required Readings:

Solving olympiad geometry without human demonstrations

  • Trieu H. Trinh, Yuhuai Wu, Quoc V. Le, He He & Thang Luong
  • Nature volume 625, pages476–482 (2024)Cite this article
  • Published: 17 January 2024
  • https://www.nature.com/articles/s41586-023-06747-5
  • Proving mathematical theorems at the olympiad level represents a notable milestone in human-level automated reasoning1,2,3,4, owing to their reputed difficulty among the world’s best talents in pre-university mathematics. Current machine-learning approaches, however, are not applicable to most mathematical domains owing to the high cost of translating human proofs into machine-verifiable format. The problem is even worse for geometry because of its unique translation challenges1,5, resulting in severe scarcity of training data. We propose AlphaGeometry, a theorem prover for Euclidean plane geometry that sidesteps the need for human demonstrations by synthesizing millions of theorems and proofs across different levels of complexity. AlphaGeometry is a neuro-symbolic system that uses a neural language model, trained from scratch on our large-scale synthetic data, to guide a symbolic deduction engine through infinite branching points in challenging problems. On a test set of 30 latest olympiad-level problems, AlphaGeometry solves 25, outperforming the previous best method that only solves ten problems and approaching the performance of an average International Mathematical Olympiad (IMO) gold medallist. Notably, AlphaGeometry produces human-readable proofs, solves all geometry problems in the IMO 2000 and 2015 under human expert evaluation and discovers a generalized version of a translated IMO theorem in 2004.

Mathematical discoveries from program search with large language models

  • Published: 14 December 2023
  • Bernardino Romera-Paredes, Mohammadamin Barekatain, Alexander Novikov, Matej Balog, M. Pawan Kumar, Emilien Dupont, Francisco J. R. Ruiz, Jordan S. Ellenberg, Pengming Wang, Omar Fawzi, Pushmeet Kohli & Alhussein Fawzi
  • Nature https://www.nature.com/articles/s41586-023-06924-6#auth-Bernardino-Romera_Paredes-Aff1
  • Large language models (LLMs) have demonstrated tremendous capabilities in solving complex tasks, from quantitative reasoning to understanding natural language. However, LLMs sometimes suffer from confabulations (or hallucinations), which can result in them making plausible but incorrect statements1,2. This hinders the use of current large models in scientific discovery. Here we introduce FunSearch (short for searching in the function space), an evolutionary procedure based on pairing a pretrained LLM with a systematic evaluator. We demonstrate the effectiveness of this approach to surpass the best-known results in important problems, pushing the boundary of existing LLM-based approaches3. Applying FunSearch to a central problem in extremal combinatorics—the cap set problem—we discover new constructions of large cap sets going beyond the best-known ones, both in finite dimensional and asymptotic cases. This shows that it is possible to make discoveries for established open problems using LLMs. We showcase the generality of FunSearch by applying it to an algorithmic problem, online bin packing, finding new heuristics that improve on widely used baselines. In contrast to most computer search approaches, FunSearch searches for programs that describe how to solve a problem, rather than what the solution is. Beyond being an effective and scalable strategy, discovered programs tend to be more interpretable than raw solutions, enabling feedback loops between domain experts and FunSearch, and the deployment of such programs in real-world applications.

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

  • Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y.K. Li, Y. Wu, Daya Guo
  • Mathematical reasoning poses a significant challenge for language models due to its complex and structured nature. In this paper, we introduce DeepSeekMath 7B, which continues pre-training DeepSeek-Coder-Base-v1.5 7B with 120B math-related tokens sourced from Common Crawl, together with natural language and code data. DeepSeekMath 7B has achieved an impressive score of 51.7% on the competition-level MATH benchmark without relying on external toolkits and voting techniques, approaching the performance level of Gemini-Ultra and GPT-4. Self-consistency over 64 samples from DeepSeekMath 7B achieves 60.9% on MATH. The mathematical reasoning capability of DeepSeekMath is attributed to two key factors: First, we harness the significant potential of publicly available web data through a meticulously engineered data selection pipeline. Second, we introduce Group Relative Policy Optimization (GRPO), a variant of Proximal Policy Optimization (PPO), that enhances mathematical reasoning abilities while concurrently optimizing the memory usage of PPO.
  • Elements:
    • Both Deepseek and Qwen use GRPO in post-training! Group Relative Policy Optimization or GRPO was introduced in the DeepSeekMath Paper last year to improve mathematical reasoning capabilities with less memory consumption, but is now used in an online way also to improve Truthfulness, Helpfulness, Conciseness…
    • Generate multiple outputs for each input question using the current Policy
    • Score these outputs using a reward model
    • Average the rewards and use it as a baseline to compute the advantages
    • Update the Policy to maximize the GRPO objective, which includes the advantages and a KL term
  • Insights:
    • Doesn’t need value function model, reducing memory and complexity
    • Adds KL term directly to the loss rather than in the reward
    • Works with rule-based Reward Models and Generative/Score based RM
    • Looks similar to RLOO method
    • DS 3 improved coding, math, writing, role-playing, and question answering

DeepSeek-V3 Technical Report

  • DeepSeek-AI, (100 additional authors not shown)
  • We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. Furthermore, DeepSeek-V3 pioneers an auxiliary-loss-free strategy for load balancing and sets a multi-token prediction training objective for stronger performance. We pre-train DeepSeek-V3 on 14.8 trillion diverse and high-quality tokens, followed by Supervised Fine-Tuning and Reinforcement Learning stages to fully harness its capabilities. Comprehensive evaluations reveal that DeepSeek-V3 outperforms other open-source models and achieves performance comparable to leading closed-source models. Despite its excellent performance, DeepSeek-V3 requires only 2.788M H800 GPU hours for its full training. In addition, its training process is remarkably stable. Throughout the entire training process, we did not experience any irrecoverable loss spikes or perform any rollbacks. The model checkpoints are available at this https URL.

More Readings:

Large Language Models for Mathematical Reasoning: Progresses and Challenges

  • Janice Ahn, Rishu Verma, Renze Lou, Di Liu, Rui Zhang, Wenpeng Yin
  • [Submitted on 31 Jan 2024 (v1), last revised 16 Sep 2024 (this version, v4)]
  • Mathematical reasoning serves as a cornerstone for assessing the fundamental cognitive capabilities of human intelligence. In recent times, there has been a notable surge in the development of Large Language Models (LLMs) geared towards the automated resolution of mathematical problems. However, the landscape of mathematical problem types is vast and varied, with LLM-oriented techniques undergoing evaluation across diverse datasets and settings. This diversity makes it challenging to discern the true advancements and obstacles within this burgeoning field. This survey endeavors to address four pivotal dimensions: i) a comprehensive exploration of the various mathematical problems and their corresponding datasets that have been investigated; ii) an examination of the spectrum of LLM-oriented techniques that have been proposed for mathematical problem-solving; iii) an overview of factors and concerns affecting LLMs in solving math; and iv) an elucidation of the persisting challenges within this domain. To the best of our knowledge, this survey stands as one of the first extensive examinations of the landscape of LLMs in the realm of mathematics, providing a holistic perspective on the current state, accomplishments, and future challenges in this rapidly evolving field.

A Survey of Deep Learning for Mathematical Reasoning

  • Pan Lu, Liang Qiu, Wenhao Yu, Sean Welleck, Kai-Wei Chang
  • [Submitted on 20 Dec 2022 (v1), last revised 22 Jun 2023 (this version, v2)]
  • Mathematical reasoning is a fundamental aspect of human intelligence and is applicable in various fields, including science, engineering, finance, and everyday life. The development of artificial intelligence (AI) systems capable of solving math problems and proving theorems has garnered significant interest in the fields of machine learning and natural language processing. For example, mathematics serves as a testbed for aspects of reasoning that are challenging for powerful deep learning models, driving new algorithmic and modeling advances. On the other hand, recent advances in large-scale neural language models have opened up new benchmarks and opportunities to use deep learning for mathematical reasoning. In this survey paper, we review the key tasks, datasets, and methods at the intersection of mathematical reasoning and deep learning over the past decade. We also evaluate existing benchmarks and methods, and discuss future research directions in this domain.

AI Capabilities Can Be Significantly Improved Without Expensive Retraining

  • https://epoch.ai/blog/ai-capabilities-can-be-significantly-improved-without-expensive-retraining

[5]: advanced LLM - for code reasoning


Reasoning

In this session, our readings cover:

Required Readings:

Agent for software engineering

  • https://www.phontron.com/slides/neubig24softwareagents.pdf

Language Models for Code Optimization: Survey, Challenges and Future Directions

  • https://arxiv.org/abs/2501.01277
  • [Submitted on 2 Jan 2025 (v1), last revised 3 Jan 2025 (this version, v2)]
  • Jingzhi Gong, Vardan Voskanyan, Paul Brookes, Fan Wu, Wei Jie, Jie Xu, Rafail Giavrimis, Mike Basios, Leslie Kanthan, Zheng Wang
  • Language models (LMs) built upon deep neural networks (DNNs) have recently demonstrated breakthrough effectiveness in software engineering tasks such as code generation, completion, and repair. This has paved the way for the emergence of LM-based code optimization techniques, which are crucial for enhancing the performance of existing programs, such as accelerating program execution time. However, a comprehensive survey dedicated to this specific application has been lacking. To fill this gap, we present a systematic literature review of over 50 primary studies, identifying emerging trends and addressing 11 specialized questions. Our findings reveal five critical open challenges, such as balancing model complexity with practical usability, cross-language/performance generalizability, and building trust in AI-driven solutions. Furthermore, we provide eight future research directions to facilitate more efficient, robust, and reliable LM-based code optimization. Thereby, this study aims to provide actionable insights and foundational references for both researchers and practitioners in this rapidly evolving field.

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

  • https://arxiv.org/abs/2406.11931
  • DeepSeek-AI, Qihao Zhu, Daya Guo, Zhihong Shao, Dejian Yang, Peiyi Wang, Runxin Xu, Y. Wu, + Yukun Li, Huazuo Gao, Shirong Ma, Wangding Zeng, Xiao Bi, Zihui Gu, Hanwei Xu, Damai Dai, Kai Dong, Liyue Zhang, Yishi Piao, Zhibin Gou, Zhenda Xie, Zhewen Hao, Bingxuan Wang, Junxiao Song, Deli Chen, Xin Xie, Kang Guan, Yuxiang You, Aixin Liu, Qiushi Du, Wenjun Gao, Xuan Lu, Qinyu Chen, Yaohui Wang, Chengqi Deng, Jiashi Li, Chenggang Zhao, Chong Ruan, Fuli Luo, Wenfeng Liang
  • We present DeepSeek-Coder-V2, an open-source Mixture-of-Experts (MoE) code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. Specifically, DeepSeek-Coder-V2 is further pre-trained from an intermediate checkpoint of DeepSeek-V2 with additional 6 trillion tokens. Through this continued pre-training, DeepSeek-Coder-V2 substantially enhances the coding and mathematical reasoning capabilities of DeepSeek-V2, while maintaining comparable performance in general language tasks. Compared to DeepSeek-Coder-33B, DeepSeek-Coder-V2 demonstrates significant advancements in various aspects of code-related tasks, as well as reasoning and general capabilities. Additionally, DeepSeek-Coder-V2 expands its support for programming languages from 86 to 338, while extending the context length from 16K to 128K. In standard benchmark evaluations, DeepSeek-Coder-V2 achieves superior performance compared to closed-source models such as GPT4-Turbo, Claude 3 Opus, and Gemini 1.5 Pro in coding and math benchmarks.

Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback

  • [Submitted on 25 Mar 2024 (v1), last revised 11 Jun 2024 (this version, v3)]
  • Zhangqian Bi, Yao Wan, Zheng Wang, Hongyu Zhang, Batu Guan, Fangxin Lu, Zili Zhang, Yulei Sui, Hai Jin, Xuanhua Shi
  • Large Language Models (LLMs) have shown remarkable progress in automated code generation. Yet, LLM-generated code may contain errors in API usage, class, data structure, or missing project-specific information. As much of this project-specific context cannot fit into the prompts of LLMs, we must find ways to allow the model to explore the project-level code context. We present CoCoGen, a new code generation approach that uses compiler feedback to improve the LLM-generated code. CoCoGen first leverages static analysis to identify mismatches between the generated code and the project’s context. It then iteratively aligns and fixes the identified errors using information extracted from the code repository. We integrate CoCoGen with two representative LLMs, i.e., GPT-3.5-Turbo and Code Llama (13B), and apply it to Python code generation. Experimental results show that CoCoGen significantly improves the vanilla LLMs by over 80% in generating code dependent on the project context and consistently outperforms the existing retrieval-based code generation baselines.

More Readings:




Here is a name list of posts!