论文检索

Applications

Wei Tao, Yucheng Zhou, Yanlin Wang, Wenqiang Zhang, Hongyu Zhang, Yu Cheng

In software development, resolving the emergent issues within GitHub repositories is a complex challenge that involves not only the incorporation of new code but also the maintenance of existing code.Large Language Models (LLMs) have shown promise in code generation but face difficulties in resolving Github issues, particularly at the repository level. To overcome this challenge, we empirically study the reason why LLMs fail to resolve GitHub issues and analyze the major factors. Motivated by the empirical findings, we propose a novel LLM-based **M**ulti-**A**gent framework for **G**itHub **I**ssue re**S**olution, **MAGIS**, consisting of four agents customized for software evolution: Manager, Repository Custodian, Developer, and Quality Assurance Engineer agents. This framework leverages the collaboration of various agents in the planning and coding process to unlock the potential of LLMs to resolve GitHub issues. In experiments, we employ the SWE-bench benchmark to compare MAGIS with popular LLMs, including GPT-3.5, GPT-4, and Claude-2. MAGIS can resolve **13.94%** GitHub issues, significantly outperforming the baselines.Specifically, MAGIS achieves an eight-fold increase in resolved ratio over the direct application of GPT-4, the advanced LLM.

Theory · Reinforcement Learning and Planning

Jincheng Mei, Bo Dai, Alekh Agarwal, Sharan Vaswani, Anant Raj, Csaba Szepesvari, Dale Schuurmans

We provide a new understanding of the stochastic gradient bandit algorithm by showing that it converges to a globally optimal policy almost surely using \emph{any} constant learning rate. This result demonstrates that the stochastic gradient algorithm continues to balance exploration and exploitation appropriately even in scenarios where standard smoothness and noise control assumptions break down. The proofs are based on novel findings about action sampling rates and the relationship between cumulative progress and noise, and extend the current understanding of how simple stochastic gradient methods behave in bandit settings.

Theory · Reinforcement Learning and Planning

Tyler Sam, Yudong Chen, Christina Yu

Many reinforcement learning (RL) algorithms are too costly to use in practice due to the large sizes $S,A$ of the problem's state and action space. To resolve this issue, we study transfer RL with latent low rank structure. We consider the problem of transferring a latent low rank representation when the source and target MDPs have transition kernels with Tucker rank $(S, d, A)$, $(S ,S , d), (d, S , A )$, or $(d , d , d )$. In each setting, we introduce the transfer-ability coefficient $\alpha$ that measures the difficulty of representational transfer. Our algorithm learns latent representations in each source MDP and then exploits the linear structure to remove the dependence on $S , A $, or $SA $ in the target MDP regret bound. We complement our positive results with information theoretic lower bounds that show our algorithms (excluding the ($d, d, d$) setting) are minimax-optimal with respect to $\alpha$.

Generative Models

Yujia Zhou, Zheng Liu, Zhicheng Dou

The emergence of Large Language Models (LLMs) has significantly advanced natural language processing, but these models often generate factually incorrect information, known as "hallucination." Initial retrieval-augmented generation (RAG) methods like the "Retrieve-Read" framework was inadequate for complex reasoning tasks. Subsequent prompt-based RAG strategies and Supervised Fine-Tuning (SFT) methods improved performance but required frequent retraining and risked altering foundational LLM capabilities. To cope with these challenges, we propose Assistant-based Retrieval-Augmented Generation (AssistRAG), integrating an intelligent information assistant within LLMs. This assistant manages memory and knowledge through tool usage, action execution, memory building, and plan specification. Using a two-phase training approach—Curriculum Assistant Learning and Reinforced Preference Optimization—AssistRAG enhances information retrieval and decision-making. Experiments show AssistRAG significantly outperforms benchmarks, especially benefiting less advanced LLMs, by providing superior reasoning capabilities and accurate responses.

Reinforcement Learning · Planning

Ye Tian, Baolin Peng, Linfeng Song, Lifeng Jin, Dian Yu, Lei Han, Haitao Mi, Dong Yu

Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning. Self-correction and self-learning emerge as viable solutions, employing strategies that allow LLMs to refine their outputs and learn from self-assessed rewards. Yet, the efficacy of LLMs in self-refining its response, particularly in complex reasoning and planning task, remains dubious. In this paper, we introduce AlphaLLM for the self-improvements of LLMs, which integrates Monte Carlo Tree Search (MCTS) with LLMs to establish a self-improving loop, thereby enhancing the capabilities of LLMs without additional annotations. Drawing inspiration from the success of AlphaGo, AlphaLLM addresses the unique challenges of combining MCTS with LLM for self-improvement, including data scarcity, the vastness search spaces of language tasks, and the subjective nature of feedback in language tasks. AlphaLLM is comprised of prompt synthesis component, an efficient MCTS approach tailored for language tasks, and a trio of critic models for precise feedback. Our experimental results in mathematical reasoning tasks demonstrate that AlphaLLM significantly enhances the performance of LLMs without additional annotations, showing the potential for self-improvement in LLMs.

Language

Zichao Li, Yanshuai Cao, Jackie CK Cheung

How do large language models (LLMs) encode the state of the world, including the status of entities and their relations, as described by a text? While existing work directly probes for a complete state of the world, our research explores whether and how LLMs abstract this world state in their internal representations. We propose a new framework for probing for world representations through the lens of state abstraction theory from reinforcement learning, which emphasizes different levels of abstraction, distinguishing between general abstractions that facilitate predicting future states and goal-oriented abstractions that guide the subsequent actions to accomplish tasks. To instantiate this framework, we design a text-based planning task, where an LLM acts as an agent in an environment and interacts with objects in containers to achieve a specified goal state. Our experiments reveal that fine-tuning as well as advanced pre-training strengthens LLM-built representations' tendency of maintaining goal-oriented abstractions during decoding, prioritizing task completion over recovery of the world's state and dynamics.

Neuroscience, Cognitive Science

Ramy Mounir, Sudeep Sarkar

Sequential memory, the ability to form and accurately recall a sequence of events or stimuli in the correct order, is a fundamental prerequisite for biological and artificial intelligence as it underpins numerous cognitive functions (e.g., language comprehension, planning, episodic memory formation, etc.) However, existing methods of sequential memory suffer from catastrophic forgetting, limited capacity, slow iterative learning procedures, low-order Markov memory, and, most importantly, the inability to represent and generate multiple valid future possibilities stemming from the same context. Inspired by biologically plausible neuroscience theories of cognition, we propose Predictive Attractor Models (PAM), a novel sequence memory architecture with desirable generative properties. PAM is a streaming model that learns a sequence in an online, continuous manner by observing each input only once. Additionally, we find that PAM avoids catastrophic forgetting by uniquely representing past context through lateral inhibition in cortical minicolumns, which prevents new memories from overwriting previously learned knowledge. PAM generates future predictions by sampling from a union set of predicted possibilities; this generative ability is realized through an attractor model trained alongside the predictor. We show that PAM is trained with local computations through Hebbian plasticity rules in a biologically plausible framework. Other desirable traits (e.g., noise tolerance, CPU-based learning, capacity scaling) are discussed throughout the paper. Our findings suggest that PAM represents a significant step forward in the pursuit of biologically plausible and computationally efficient sequential memory models, with broad implications for cognitive science and artificial intelligence research. Illustration videos and code are available on our project page: https://ramymounir.com/publications/pam.

Reinforcement Learning · Planning

Michael Katz, Harsha Kokel, Kavitha Srinivas, Shirin Sohrabi Araghi

Among the most important properties of algorithms investigated in computer science are soundness, completeness, and complexity. These properties, however, are rarely analyzed for the vast collection of recently proposed methods for planning with large language models. In this work, we alleviate this gap. We analyse these properties of using LLMs for planning and highlight that recent trends abandon both soundness and completeness for the sake of inefficiency. We propose a significantly more efficient approach that can, at the same time, maintain both soundness and completeness. We exemplify on four representative search problems, comparing to the LLM-based solutions from the literature that attempt to solve these problems. We show that by using LLMs to produce the code for the search components we can solve the entire datasets with 100% accuracy with only a few calls to the LLM. In contrast, the compared approaches require hundreds of thousands of calls and achieve significantly lower accuracy. We argue for a responsible use of compute resources; urging research community to investigate sound and complete LLM-based approaches that uphold efficiency.

Theory · Reinforcement Learning and Planning

Pietro Novelli, Marco Pratticò, Massimiliano Pontil, Carlo Ciliberto

Policy Mirror Descent (PMD) is a powerful and theoretically sound methodology for sequential decision-making. However, it is not directly applicable to Reinforcement Learning (RL) due to the inaccessibility of explicit action-value functions. We address this challenge by introducing a novel approach based on learning a world model of the environment using conditional mean embeddings. Leveraging tools from operator theory we derive a closed-form expression of the action-value function in terms of the world model via simple matrix operations. Combining these estimators with PMD leads to POWR, a new RL algorithm for which we prove convergence rates to the global optimum. Preliminary experiments in finite and infinite state settings support the effectiveness of our method.

Generative Models · Reasoning

Kaya Stechly, Karthik Valmeekam, Subbarao Kambhampati

Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution. Previous work has claimed that this can be mitigated with chain of thought prompting--a method of demonstrating solution procedures--with the intuition that it is possible to in-context teach an LLM an algorithm for solving the problem.This paper presents a case study of chain of thought on problems from Blocksworld, a classical planning domain, and examines the performance of two state-of-the-art LLMs across two axes: generality of examples given in prompt, and complexity of problems queried with each prompt. While our problems are very simple, we only find meaningful performance improvements from chain of thought prompts when those prompts are exceedingly specific to their problem class, and that those improvements quickly deteriorate as the size n of the query-specified stack grows past the size of stacks shown in the examples.We also create scalable variants of three domains commonly studied in previous CoT papers and demonstrate the existence of similar failure modes.Our results hint that, contrary to previous claims in the literature, CoT's performance improvements do not stem from the model learning general algorithmic procedures via demonstrations but depend on carefully engineering highly problem specific prompts. This spotlights drawbacks of chain of thought, especially the sharp tradeoff between possible performance gains and the amount of human labor necessary to generate examples with correct reasoning traces.

Weiyu Ma, Qirui Mi, Yongcheng Zeng, Xue Yan, Runji Lin, Yuqiao Wu, Jun Wang, Haifeng Zhang

With the continued advancement of Large Language Models (LLMs) Agents in reasoning, planning, and decision-making, benchmarks have become crucial in evaluating these skills. However, there is a notable gap in benchmarks for real-time strategic decision-making. StarCraft II (SC2), with its complex and dynamic nature, serves as an ideal setting for such evaluations. To this end, we have developed TextStarCraft II, a specialized environment for assessing LLMs in real-time strategic scenarios within SC2. Addressing the limitations of traditional Chain of Thought (CoT) methods, we introduce the Chain of Summarization (CoS) method, enhancing LLMs' capabilities in rapid and effective decision-making. Our key experiments included:1. LLM Evaluation: Tested 10 LLMs in TextStarCraft II, most of them defeating LV5 build-in AI, showcasing effective strategy skills.2. Commercial Model Knowledge: Evaluated four commercial models on SC2 knowledge; GPT-4 ranked highest by Grandmaster-level experts.3. Human-AI Matches: Experimental results showed that fine-tuned LLMs performed on par with Gold-level players in real-time matches, demonstrating comparable strategic abilities.All code and data from thisstudy have been made pulicly available at https://github.com/histmeisah/Large-Language-Models-play-StarCraftII

Theory · Reinforcement Learning and Planning

Xuan Bach Le, Dominik Wagner, Leon Witzman, Alexander Rabinovich, Luke Ong

Linear temporal logic (LTL) and, more generally, $\omega$-regular objectives are alternatives to the traditional discount sum and average reward objectives in reinforcement learning (RL), offering the advantage of greater comprehensibility and hence explainability. In this work, we study the relationship between these objectives. Our main result is that each RL problem for $\omega$-regular objectives can be reduced to a limit-average reward problem in an optimality-preserving fashion, via (finite-memory) reward machines. Furthermore, we demonstrate the efficacy of this approach by showing that optimal policies for limit-average problems can be found asymptotically by solving a sequence of discount-sum problems approximately. Consequently, we resolve an open problem: optimal policies for LTL and $\omega$-regular objectives can be learned asymptotically.

Reinforcement Learning · Planning

Zizhao Wang, Jiaheng Hu, Caleb Chuck, Stephen Chen, Roberto Martín-Martín, Amy Zhang, Scott Niekum, Peter Stone

Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable skills through autonomous, reward-free interactions with environments. Existing unsupervised skill discovery methods learn skills by encouraging distinguishable behaviors that cover diverse states. However, in complex environments with many state factors (e.g., household environments with many objects), learning skills that cover all possible states is impossible, and naively encouraging state diversity often leads to simple skills that are not ideal for solving downstream tasks. This work introduces Skill Discovery from Local Dependencies (SkiLD), which leverages state factorization as a natural inductive bias to guide the skill learning process. The key intuition guiding SkiLD is that skills that induce \textbf{diverse interactions} between state factors are often more valuable for solving downstream tasks. To this end, SkiLD develops a novel skill learning objective that explicitly encourages the mastering of skills that effectively induce different interactions within an environment. We evaluate SkiLD in several domains with challenging, long-horizon sparse reward tasks including a realistic simulated household robot domain, where SkiLD successfully learns skills with clear semantic meaning and shows superior performance compared to existing unsupervised reinforcement learning methods that only maximize state coverage.

Reinforcement Learning · Deep RL

Miles Hutson, Isaac Kauvar, Nick Haber

Model-based reinforcement learning (MBRL) is a promising route to sample-efficient policy optimization. However, a known vulnerability of reconstruction-based MBRL consists of scenarios in which detailed aspects of the world are highly predictable, but irrelevant to learning a good policy. Such scenarios can lead the model to exhaust its capacity on meaningless content, at the cost of neglecting important environment dynamics. While existing approaches attempt to solve this problem, we highlight its continuing impact on leading MBRL methods ---including DreamerV3 and DreamerPro--- with a novel environment where background distractions are intricate, predictable, and useless for planning future actions. To address this challenge we develop a method for focusing the capacity of the world model through a synergy of a pretrained segmentation model, a task-aware reconstruction loss, and adversarial learning. Our method outperforms a variety of other approaches designed to reduce the impact of distractors, and is an advance towards robust model-based reinforcement learning.

Optimization

Peter Halmos, Xinhao Liu, Julian Gold, Benjamin Raphael

Optimal transport (OT) is a general framework for finding a minimum-cost transport plan, or coupling, between probability distributions, and has many applications in machine learning. A key challenge in applying OT to massive datasets is the quadratic scaling of the coupling matrix with the size of the dataset. [Forrow et al. 2019] introduced a factored coupling for the k-Wasserstein barycenter problem, which [Scetbon et al. 2021] adapted to solve the primal low-rank OT problem. We derive an alternative parameterization of the low-rank problem based on the _latent coupling_ (LC) factorization previously introduced by [Lin et al. 2021] generalizing [Forrow et al. 2019]. The LC factorization has multiple advantages for low-rank OT including decoupling the problem into three OT problems and greater flexibility and interpretability. We leverage these advantages to derive a new algorithm _Factor Relaxation with Latent Coupling_ (FRLC), which uses _coordinate_ mirror descent to compute the LC factorization. FRLC handles multiple OT objectives (Wasserstein, Gromov-Wasserstein, Fused Gromov-Wasserstein), and marginal constraints (balanced, unbalanced, and semi-relaxed) with linear space complexity. We provide theoretical results on FRLC, and demonstrate superior performance on diverse applications -- including graph clustering and spatial transcriptomics -- while demonstrating its interpretability.

Language

Ouail Kitouni, Niklas S Nolte, Adina Williams, Michael Rabbat, Diane Bouchacourt, Mark Ibrahim

Today's best language models still struggle with "hallucinations", factually incorrect generations, which impede their ability to reliably retrieve information seen during training. The *reversal curse*, where models cannot recall information when probed in a different order than was encountered during training, exemplifies limitations in information retrieval. To better understand these limitations, we reframe the reversal curse as a *factorization curse* --- a failure of models to learn the same joint distribution under different factorizations.We more closely simulate finetuning workflows which train pretrained models on specialized knowledge by introducing*WikiReversal*, a realistic testbed based on Wikipedia knowledge graphs. Through a series of controlled experiments with increasing levels of realism, including non-reciprocal relations, we find that reliable information retrieval is an inherent failure of the next-token prediction objective used in popular large language models. Moreover, we demonstrate reliable information retrieval cannot be solved with scale, reversed tokens, or even naive bidirectional-attention training. Consequently, various approaches to finetuning on specialized data would necessarily provide mixed results on downstream tasks, unless the model has already seen the right sequence of tokens. Across five tasks of varying levels of complexity, our results uncover a promising path forward: factorization-agnostic objectives can significantly mitigate the reversal curse and hint at improved knowledge storage and planning capabilities.

Optimization · Optimization and Learning under Uncertainty

Jose Pablo Folch, Calvin Tsay, Robert Lee, Behrang Shafei, Weronika Ormaniec, Andreas Krause, Mark van der Wilk, Ruth Misener, Mojmir Mutny

Bayesian optimization is a methodology to optimize black-box functions. Traditionally, it focuses on the setting where you can arbitrarily query the search space. However, many real-life problems do not offer this flexibility; in particular, the search space of the next query may depend on previous ones. Example challenges arise in the physical sciences in the form of local movement constraints, required monotonicity in certain variables, and transitions influencing the accuracy of measurements. Altogether, such *transition constraints* necessitate a form of planning. This work extends classical Bayesian optimization via the framework of Markov Decision Processes. We iteratively solve a tractable linearization of our utility function using reinforcement learning to obtain a policy that plans ahead for the entire horizon. This is a parallel to the optimization of an *acquisition function in policy space*. The resulting policy is potentially history-dependent and non-Markovian. We showcase applications in chemical reactor optimization, informative path planning, machine calibration, and other synthetic examples.

Datasets and Benchmarks

Rudolf Laine, Bilal Chughtai, Jan Betley, Kaivalya Hariharan, Mikita Balesni, Jérémy Scheurer, Marius Hobbhahn, Alexander Meinke, Owain Evans

AI assistants such as ChatGPT are trained to respond to users by saying, "I am a large language model”.This raises questions. Do such models "know'' that they are LLMs and reliably act on this knowledge? Are they "aware" of their current circumstances, such as being deployed to the public?We refer to a model's knowledge of itself and its circumstances as **situational awareness**.To quantify situational awareness in LLMs, we introduce a range of behavioral tests, based on question answering and instruction following. These tests form the **Situational Awareness Dataset (SAD)**, a benchmark comprising 7 task categories and over 13,000 questions.The benchmark tests numerous abilities, including the capacity of LLMs to (i) recognize their own generated text, (ii) predict their own behavior, (iii) determine whether a prompt is from internal evaluation or real-world deployment, and (iv) follow instructions that depend on self-knowledge.We evaluate 16 LLMs on SAD, including both base (pretrained) and chat models.While all models perform better than chance, even the highest-scoring model (Claude 3 Opus) is far from a human baseline on certain tasks. We also observe that performance on SAD is only partially predicted by metrics of general knowledge. Chat models, which are finetuned to serve as AI assistants, outperform their corresponding base models on SAD but not on general knowledge tasks.The purpose of SAD is to facilitate scientific understanding of situational awareness in LLMs by breaking it down into quantitative abilities. Situational awareness is important because it enhances a model's capacity for autonomous planning and action. While this has potential benefits from automation, it also introduces novel risks related to AI safety and control.

Datasets and Benchmarks

Anna Varbella, Kenza Amara, Blazhe Gjorgiev, Mennatallah El-Assady, Giovanni Sansavini

Power grids are critical infrastructures of paramount importance to modern society and, therefore, engineered to operate under diverse conditions and failures. The ongoing energy transition poses new challenges for the decision-makers and system operators. Therefore, we must develop grid analysis algorithms to ensure reliable operations. These key tools include power flow analysis and system security analysis, both needed for effective operational and strategic planning. The literature review shows a growing trend of machine learning (ML) models that perform these analyses effectively. In particular, Graph Neural Networks (GNNs) stand out in such applications because of the graph-based structure of power grids. However, there is a lack of publicly available graph datasets for training and benchmarking ML models in electrical power grid applications. First, we present PowerGraph, which comprises GNN-tailored datasets for i) power flows, ii) optimal power flows, and iii) cascading failure analyses of power grids. Second, we provide ground-truth explanations for the cascading failure analysis. Finally, we perform a complete benchmarking of GNN methods for node-level and graph-level tasks and explainability. Overall, PowerGraph is a multifaceted GNN dataset for diverse tasks that includes power flow and fault scenarios with real-world explanations, providing a valuable resource for developing improved GNN models for node-level, graph-level tasks and explainability methods in power system modeling. The dataset is available at https://figshare.com/articles/dataset/PowerGraph/22820534 and the code at https://github.com/PowerGraph-Datasets.

Xian Wu, Yutian Zhao, Yunyan Zhang, Jiageng Wu, Zhihong Zhu, Yingying Zhang, Yi Ouyang, Ziheng Zhang, Huimin WANG, zhenxi Lin 等

Large language models (LLMs) have demonstrated remarkable capabilities in language understanding and generation, leading to their widespread adoption across various fields. Among these, the medical field is particularly well-suited for LLM applications, as many medical tasks can be enhanced by LLMs. Despite the existence of benchmarks for evaluating LLMs in medical question-answering and exams, there remains a notable gap in assessing LLMs' performance in supporting patients throughout their entire hospital visit journey in real-world clinical practice. In this paper, we address this gap by dividing a typical patient's clinical journey into four stages: planning, access, delivery and ongoing care. For each stage, we introduce multiple tasks and corresponding datasets, resulting in a comprehensive benchmark comprising 12 datasets, of which five are newly introduced, and seven are constructed from existing datasets. This proposed benchmark facilitates a thorough evaluation of LLMs' effectiveness across the entire patient journey, providing insights into their practical application in clinical settings. Additionally, we evaluate three categories of LLMs against this benchmark: 1) proprietary LLM services such as GPT-4; 2) public LLMs like QWen; and 3) specialized medical LLMs, like HuatuoGPT2. Through this extensive evaluation, we aim to provide a better understanding of LLMs' performance in the medical domain, ultimately contributing to their more effective deployment in healthcare settings.