Related papers: SEA-Eval: A Benchmark for Evaluating Self-Evolving…

Reinforcement Learning (RL) has demonstrated significant potential in enhancing the reasoning capabilities of large language models (LLMs). However, the success of RL for LLMs heavily relies on human-curated datasets and verifiable rewards,…

Reinforcement learning (RL) has been pivotal in enhancing the reasoning capabilities of large language models (LLMs), but it often suffers from limited exploration and entropy collapse, where models exploit a narrow set of solutions,…

LLM-based evolution has emerged as a promising way to improve agents by refining non-parametric artifacts, but its wall-clock cost remains a major bottleneck. We identify that this cost comes from synchronized stage execution and imbalance…

Reinforcement learning (RL) provides a naturalistic framing for learning through trial and error, which is appealing both because of its simplicity and effectiveness and because of its resemblance to how humans and animals acquire skills…

Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through…

Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn interaction and tool use. Scaling such systems exposes two…

LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks freeze a curated task set at release time and grade mainly the final response, making it…

Current LLM agent benchmarks, which predominantly focus on binary pass/fail tasks such as code generation or search-based question answering, often neglect the value of real-world engineering that is often captured through the iterative…

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…

Multi-agents has exhibited significant intelligence in real-word simulations with Large language models (LLMs) due to the capabilities of social cognition and knowledge retrieval. However, existing research on agents equipped with effective…

Large Language Models have demonstrated remarkable capabilities across diverse domains, yet significant challenges persist when deploying them as AI agents for real-world long-horizon tasks. Existing LLM agents suffer from a critical…

Reinforcement learning for LLM agents is typically conducted on a static data distribution, which fails to adapt to the agent's evolving behavior and leads to poor coverage of complex environment interactions. To address these challenges,…

The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…

Surrogate-assisted evolutionary algorithms (SAEAs) are recently among the most widely studied methods for their capability to solve expensive real-world optimization problems. However, the development of new methods and benchmarking with…

Recent advances have enabled large language model (LLM) agents to solve complex tasks by orchestrating external tools. However, these agents often struggle in specialized, tool-intensive domains that demand long-horizon execution, tight…

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards…

Large Language Models (LLMs) increasingly act as function-call agents that invoke external tools to tackle tasks beyond their static knowledge. However, they typically invoke tools one at a time without a global view of task structure. As…

Recently, LLM agents have made rapid progress in improving their programming capabilities. However, existing benchmarks lack the ability to automatically evaluate from users' perspective, and also lack the explainability of the results of…

Evaluating large language models (LLMs) in complex decision-making is essential for advancing AI's ability for strategic planning and real-time adaptation. However, existing benchmarks for tasks like StarCraft II fail to capture the game's…

Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to self-adapt by…