Related papers: RAGEN: Understanding Self-Evolution in LLM Agents …

Retrieval-augmented generation (RAG) systems face a fundamental challenge in aligning independently developed retrievers and large language models (LLMs). Existing approaches typically involve modifying either component or introducing…

While reinforcement learning (RL) can empower autonomous agents by enabling self-improvement through interaction, its practical adoption remains challenging due to costly rollouts, limited task diversity, unreliable reward signals, and…

Reward design is a key component of deep reinforcement learning, yet some tasks and designer's objectives may be unnatural to define as a scalar cost function. Among the various techniques, formal methods integrated with DRL have garnered…

Can large language model (LLM) agents reproduce the complex social dynamics that characterize human online behavior -- shaped by homophily, reciprocity, and social validation -- and what memory and learning mechanisms enable such dynamics…

With extensive pre-trained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects such as multi-task learning, sample efficiency, and…

Self-supervised reinforcement learning (RL) presents a promising approach for enhancing the reasoning capabilities of Large Language Models (LLMs) without reliance on expensive human-annotated data. However, we find that existing methods…

Large pretrained models are showing increasingly better performance in reasoning and planning tasks across different modalities, opening the possibility to leverage them for complex sequential decision making problems. In this paper, we…

Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks. Existing implementations typically rely on a single agent, but they suffer from limited context…

Effective interactive tool use requires agents to master Tool Integrated Reasoning (TIR): a complex process involving multi-turn planning and long-context dialogue management. To train agents for this dynamic process, particularly in…

Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. While reinforcement learning (RL) has been shown to improve performance in this paradigm, its contributions remain…

RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track reasoning stability. However, entropy only measures diversity within the same input,…

Feature transformation enhances downstream task performance by generating informative features through mathematical feature crossing. Despite the advancements in deep learning, feature transformation remains essential for structured data,…

Large language models (LLMs) struggle in real-world clinical consultations. Single-turn consultation systems require patients to describe all symptoms at once, which often leads to unclear complaints and vague diagnoses. Traditional…

Standard reinforcement learning (RL) for large language model (LLM) agents typically optimizes extrinsic rewards, prioritizing isolated task completion over continual adaptation. Consequently, agents often converge to suboptimal policies…

We propose a novel approach to address one aspect of the non-stationarity problem in multi-agent reinforcement learning (RL), where the other agents may alter their policies due to environment changes during execution. This violates the…

Reinforcement learning (RL) has achieved remarkable success in fields like robotics and autonomous driving, but adversarial attacks designed to mislead RL systems remain challenging. Existing approaches often rely on modifying the…

Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking -- enabling models to monitor, evaluate, and control their reasoning processes for more adaptive and…

Large language models (LLMs) demonstrate strong reasoning abilities across mathematical, strategic, and linguistic tasks, yet little is known about how well they reason in dynamic, real-time, multi-agent scenarios, such as collaborative…

Multi-agent reinforcement learning (MARL) has been increasingly adopted in many real-world applications. While MARL enables decentralized deployment on resource-constrained edge devices, it suffers from severe non-stationarity due to the…

Large Language Models (LLMs) agents are increasingly pivotal for addressing complex tasks in interactive environments. Existing work mainly focuses on enhancing performance through behavior cloning from stronger experts, yet such approaches…