Related papers: EvoTool: Self-Evolving Tool-Use Policy Optimizatio…

The reasoning frontier of Large Language Models (LLMs) has advanced significantly through modern post-training paradigms (e.g., Reinforcement Learning from Verifiable Rewards (RLVR)). However, the efficacy of these methods remains…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, including programming, planning, and decision-making. However, their performance often degrades when faced with highly complex problem instances…

Multi-agent reinforcement learning (MARL) has achieved significant progress in solving complex multi-player games through self-play. However, training effective adversarial policies requires millions of experience samples and substantial…

Large language model (LLM)-based agents frequently generate seemingly coherent plans that fail upon execution due to infeasible actions, constraint violations, and compounding errors over extended horizons. PIVOT (Plan-Inspect-eVOlve…

Visuomotor policies based on generative architectures such as diffusion and flow-based matching have shown strong performance but degrade under distribution shifts, demonstrating limited recovery capabilities without costly finetuning. In…

This study proposes Tool-RoCo, a novel benchmark for evaluating large language models (LLMs) in long-term multi-agent cooperation based on RoCo, a multi-robot cooperative benchmark. Recent research on LLM-based multi-agent systems has…

Reusable skills play a key role in improving LLM-based agents, but existing skill-evolution methods often fail to ensure that evolved skills both cover the knowledge required by the task and remain aligned with the target task. As a result,…

Large Language Models (LLMs) have demonstrated great potential in automating the generation of Verilog hardware description language code for hardware design. This automation is critical to reducing human effort in the complex and…

Large Language Model (LLM) based multi-agent systems (MAS) have shown promise in tackling complex tasks, but often rely on predefined roles and centralized coordination, limiting their adaptability to evolving challenges. This paper…

Reinforcement learning (RL) for LLM post-training faces a fundamental design choice: whether to use a learned critic as a baseline for policy optimization. Classical theory favors critic-based methods such as PPO for variance reduction, yet…

In recent years, the landscape of software threats has become significantly more dynamic and distributed. Security vulnerabilities are no longer discovered and shared only through formal channels such as public vulnerability databases or…

Improving vision-language models (VLMs) in the post-training stage typically relies on supervised fine-tuning or reinforcement learning, methods that necessitate costly, human-annotated data. While self-supervised techniques have proven…

Developing Large Language Model (LLM) agents that exhibit human-like behavior, encompassing not only individual heterogeneity rooted in unique user profiles but also adaptive response to socially connected neighbors, is a significant…

With AI agents increasingly deployed as long-running systems, it becomes essential to autonomously construct and continuously evolve customized software to enable interaction within dynamic environments. Yet, existing benchmarks evaluate…

Multi-agent systems (MAS) have emerged as a powerful paradigm for orchestrating large language models (LLMs) and specialized tools to collaboratively address complex tasks. However, existing MAS frameworks often require manual workflow…

Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained function, whereas a skill is a structured bundle of…

LLM-based agents are increasingly used for cybersecurity tasks, but most existing systems rely on fixed, human-designed scaffolds that struggle to adapt across diverse targets and failure modes. We introduce \textsc{CyberEvolver}, a…

As LLMs continue to shape real-world applications, automated jailbreak generation becomes essential to reveal safety weaknesses and guide model improvement. Existing automatic jailbreak generation methods have not yet fully considered two…

We introduce EvoGit, a decentralized multi-agent framework for collaborative software development driven by autonomous code evolution. EvoGit deploys a population of independent coding agents, each proposing edits to a shared codebase…

Tool use enables large language models (LLMs) to access external information, invoke software systems, and act in digital environments beyond what can be solved from model parameters alone. Early research mainly studied whether a model…