CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use
AI agents are increasingly used to solve real-world tasks by reasoning over multi-turn user interactions and invoking external tools. However, applying reinforcement learning to such settings remains difficult: realistic objectives often lack verifiable rewards and instead emphasize open-ended behaviors; moreover, RL for multi-turn, multi-step agentic tool use is still underexplored; and building and maintaining executable tool environments is costly, limiting scale and coverage. We propose CM2, an RL framework that replaces verifiable outcome rewards with checklist rewards. CM2 decomposes each turn's intended behavior into fine-grained binary criteria with explicit evidence grounding and structured metadata, turning open-ended judging into more stable classification-style decisions. To balance stability and informativeness, our method adopts a strategy of sparse reward assignment but dense evaluation criteria. Training is performed in a scalable LLM-simulated tool environment, avoiding heavy engineering for large tool sets. Experiments show that CM2 consistently improves over supervised fine-tuning. Starting from an 8B Base model and training on an 8k-example RL dataset, CM2 improves over the SFT counterpart by 8 points on tau^-Bench, by 10 points on BFCL-V4, and by 12 points on ToolSandbox. The results match or even outperform similarly sized open-source baselines, including the judging model. CM2 thus provides a scalable recipe for optimizing multi-turn, multi-step tool-using agents without relying on verifiable rewards. Code provided by the open-source community: https://github.com/namezhenzhang/CM2-RLCR-Tool-Agent.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Soft-SVeRL: Self-Verified Reinforcement Learning with Soft Rewards
Reinforcement Learning from Verifiable Rewards (RLVR) has improved language models in domains such as mathematics and code, where correctness can be checked automatically. However, many important tasks are only partially…
Reinforcement LearningChecklists Are Better Than Reward Models For Aligning Language Models
Language models must be adapted to understand and follow user instructions. Reinforcement learning is widely used to facilitate this -- typically using fixed criteria such as "helpfulness" and "harmfulness". In our work,…
Reinforcement LearningInstruction FollowingFrom Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models
Reinforcement learning (RL) for large language models (LLMs) increasingly relies on sparse, outcome-level rewards -- yet determining which actions within a long trajectory caused the outcome remains difficult. This credi…
Reinforcement LearningRewarding Better Thinking for LLM Preference Alignment
LLM preference alignment aims to optimize models toward human preferences across diverse user instructions. Reinforcement learning has become a major post-training approach for this goal, but existing proxy rewards are o…
Reinforcement LearningEvoIdeator: Evolving Scientific Ideas through Checklist-Grounded Reinforcement Learning
Scientific idea generation is a cornerstone of autonomous knowledge discovery, yet the iterative evolution required to transform initial concepts into high-quality research proposals remains a formidable challenge for La…
Reinforcement Learning