# CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use

arXiv: https://arxiv.org/abs/2602.12268 · HTML: https://mlsanity.com/paper/2602.12268/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 33 of its 42 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 30 of 33)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities](https://mlsanity.com/paper/2408.04682/) (2024)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [ToolACE: Winning the Points of LLM Function Calling](https://mlsanity.com/paper/2409.00920/) (2024)
- [APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay](https://mlsanity.com/paper/2504.03601/) (2025)
- [R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents](https://mlsanity.com/paper/2504.07164/) (2025)
- [Generative Reward Models](https://mlsanity.com/paper/2410.12832/) (2024)
- [OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment](https://mlsanity.com/paper/2510.07743/) (2025)
- [Checklists Are Better Than Reward Models For Aligning Language Models](https://mlsanity.com/paper/2507.18624/) (2025)
- [Evaluating Open-Domain Question Answering in the Era of Large Language Models](https://mlsanity.com/paper/2305.06984/) (2023)
- [Simulating Environments with Reasoning Models for Agent Training](https://mlsanity.com/paper/2511.01824/) (2025)
- [MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use](https://mlsanity.com/paper/2508.18669/) (2025)
- [A Survey on Multi-Turn Interaction Capabilities of Large Language Models](https://mlsanity.com/paper/2501.09959/) (2025)
- [Rubric Is All You Need: Enhancing LLM-based Code Evaluation With Question-Specific Rubrics](https://mlsanity.com/paper/2503.23989/) (2025)
- [StepTool: Enhancing Multi-Step Tool Usage in LLMs via Step-Grained Reinforcement Learning](https://mlsanity.com/paper/2410.07745/) (2024)
- [Interleaved Reasoning for Large Language Models via Reinforcement Learning](https://mlsanity.com/paper/2505.19640/) (2025)
- [EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning](https://mlsanity.com/paper/2509.22576/) (2025)
- [Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models](https://mlsanity.com/paper/2505.16265/) (2025)

## Built on by (most cited first, 14 of 14)

- [GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation](https://mlsanity.com/paper/2605.11853/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution](https://mlsanity.com/paper/2607.26784/) (2026)
- [Beyond the Illusion of Consensus: From Surface Heuristics to Knowledge-Grounded Evaluation in LLM-as-a-Judge](https://mlsanity.com/paper/2603.11027/) (2026)
- [Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning](https://mlsanity.com/paper/2606.06976/) (2026)
- [Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning](https://mlsanity.com/paper/2608.09682/) (2026)
- [EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning](https://mlsanity.com/paper/2608.06197/) (2026)
- [TRACER: Per-Tool Context Retention for LLM Agents via Consequence-Attributed Reinforcement Learning](https://mlsanity.com/paper/2608.29363/) (2026)
- [SAP: State-Guided Data Synthesis with Argument Provenance for Multi-Turn Tool Use](https://mlsanity.com/paper/2609.06124/) (2026)
- [Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs](https://mlsanity.com/paper/2606.00726/) (2026)
- [Mint-Agent: Introducing Finance-Native Agentic Foundation Models](https://mlsanity.com/paper/2608.16386/) (2026)
- [ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning](https://mlsanity.com/paper/2609.27532/) (2026)
- [RISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation](https://mlsanity.com/paper/2610.00979/) (2026)
- [EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents](https://mlsanity.com/paper/2610.16523/) (2026)

## Abstract (arXiv)

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.