Related papers: Roles with Rails: Contract-Preserving Role Evoluti…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. However, single-model responses often exhibit inconsistencies, hallucinations, and varying quality across different…

Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experience to guide their behavior. We present the first systematic…

We propose a new framework for multi-agent reinforcement learning (MARL), where the agents cooperate in a time-evolving network with latent community structures and mixed memberships. Unlike traditional neighbor-based or fixed interaction…

Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an…

Role-based learning is a promising approach to improving the performance of Multi-Agent Reinforcement Learning (MARL). Nevertheless, without manual assistance, current role-based methods cannot guarantee stably discovering a set of roles to…

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback. However, current RLVR methods typically assign the same reward to every token.…

This paper proposes a highly robust autonomous agent framework based on the ReAct paradigm, designed to solve complex tasks through adaptive decision making and multi-agent collaboration. Unlike traditional frameworks that rely on fixed…

The pursuit of artificial agents that can learn to master complex environments has led to remarkable successes, yet prevailing deep reinforcement learning methods often rely on immense experience, encoding their knowledge opaquely within…

Large language models (LLMs) have exhibited extraordinary performance in a variety of tasks while it remains challenging for them to solve complex multi-step tasks as agents. In practice, agents sensitive to the outcome of certain key steps…

Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-session environments…

Multi-agent Retrieval-Augmented Generation (RAG), wherein each agent takes on a specific role, supports hard queries that require multiple steps and sources, or complex reasoning. Existing approaches, however, rely on static agent behaviors…

Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT…

Critique-guided reinforcement learning (RL) has emerged as a powerful paradigm for training LLM agents by augmenting sparse outcome rewards with natural-language feedback. However, current methods often rely on static or offline critic…

Multi-agent systems perform well on general reasoning tasks. However, the lack of training in specialized areas hinders their accuracy. Current training methods train a unified large language model (LLM) for all agents in the system. This…

This paper introduces SagaLLM, a structured multi-agent architecture designed to address four foundational limitations of current LLM-based planning systems: unreliable self-validation, context loss, lack of transactional safeguards, and…

The dominant paradigm for building LLM based agents is the Agent Loop, an iterative cycle where a single language model decides what to do next by reading an ever growing context window. This paradigm has three structural weaknesses:…

A large amount of work has been done in Multi-Agent Systems (MAS) for modeling and solving problems with multiple interacting agents. However, most LLMs are pretrained independently and not specifically optimized for coordination. Existing…

Constitutional AI has focused on single-model alignment using fixed principles. However, multi-agent systems create novel alignment challenges through emergent social dynamics. We present Constitutional Evolution, a framework for…

While large language model (LLM) agents have demonstrated impressive problem-solving capabilities, they typically operate as static systems, lacking the ability to evolve through lifelong interaction. Existing attempts to bridge this gap…

While Multi-Agent Systems (MAS) empower Large Language Models to tackle complex reasoning tasks through collaborative interaction, optimizing their dynamics remains a formidable challenge due to the discrete, non-differentiable nature of…