Related papers: ToolBrain: A Flexible Reinforcement Learning Frame…

Reward models (RMs) play a critical role in aligning large language models (LLMs) with human preferences. Yet in the domain of tool learning, the lack of RMs specifically designed for function-calling tasks has limited progress toward more…

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool…

Language model (LM) agents have gained significant attention for their ability to autonomously complete tasks through interactions with environments, tools, and APIs. LM agents are primarily built with prompt engineering or supervised…

Large Language Models (LLMs) enhance their problem-solving capability by utilizing external tools. However, in open-world scenarios with massive and evolving tool repositories, existing methods relying on static embedding retrieval or…

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are increasingly expected…

Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large Language Models (LLMs) and increasingly…

Current Large Language Models (LLMs) often undergo supervised fine-tuning (SFT) to acquire tool use capabilities. However, SFT struggles to generalize to unfamiliar or complex tool use scenarios. Recent advancements in reinforcement…

We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic…

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…

Advances in large language models (LLMs) have recently opened new and promising avenues for small-molecule drug discovery. Yet existing LLM-based approaches for molecular generation often suffer from high rates of invalid and low-quality…

Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this…

We study whether self-learning can scale LLM-based agents without relying on human-curated datasets or predefined rule-based rewards. Through controlled experiments in a search-agent setting, we identify two key determinants of scalable…

Large language models (LLMs) have demonstrated strong capabilities in language understanding and reasoning, yet they remain limited when tackling real-world tasks that require up-to-date knowledge, precise operations, or specialized tool…

Recent advances in large language models (LLMs) have sparked growing interest in building generalist agents that can learn through online interactions. However, applying reinforcement learning (RL) to train LLM agents in multi-turn,…

Agentic reinforcement learning (RL) has proven effective for training LLM-based agents with external tool-use capabilities. However, we identify that agentic RL training induces increasing redundant tool calls and blurs the model's…

Large language models (LLMs) are becoming the foundation for autonomous agents that can use tools to solve complex tasks. Reinforcement learning (RL) has emerged as a common approach for injecting such agentic capabilities, but typically…

The functionality of Large Language Model (LLM) agents is primarily determined by two capabilities: action planning and answer summarization. The former, action planning, is the core capability that dictates an agent's performance. However,…

Large language model alignment via reinforcement learning depends critically on reward function quality. However, static, domain-specific reward models are often costly to train and exhibit poor generalization in out-of-distribution…

The emergence of large language model (LLM)-based agents has significantly advanced the development of autonomous machine learning (ML) engineering. However, the dominant prompt-based paradigm exhibits limitations: smaller models lack the…

Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks. In realistic reasoning scenarios, LLMs can…