ACL Findings2025
LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback
Thai Quoc Hoang, Kung-Hsiang Huang, Shirley Kokane, Jianguo Zhang, Zuxin Liu, Ming Zhu, Jake Grigsby, Tian Lan, Michael S. Ryoo, Chien-Sheng Wu, Shelby Heinecke, Huan Wang
Abstract
Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to feedback. To address these issues, we present LAM SIMULATOR, a comprehensive framework designed for online exploration of agentic tasks with high-quality feedback. Our framework features a dynamic task query generator, an extensive collection of tools, and an interactive environment where Large Language Model (LLM) Agents can call tools and receive realtime feedback. This setup enables LLM Agents to explore and solve tasks autonomously, facilitating the discovery of multiple approaches to tackle any given task. The resulting action trajectory data are then used to create highquality training datasets for LAMs. Our experiments on popular agentic benchmarks, Tool-Bench and CRMArena, highlight the effectiveness of LAM SIMULATOR: models trained with self-generated datasets using our framework achieve significant performance gains, up to a 49.3% improvement over their original baselines. LAM SIMULATOR requires minimal human input during dataset creation, highlighting LAM SIMULATOR's efficiency and effectiveness in speeding up development of AI agents.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution cites Reflexion: language agents with verbal reinforcement learning
- WebArena: A Realistic Web Environment for Building Autonomous Agents cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Reflexion: language agents with verbal reinforcement learning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- AgentBench: Evaluating LLMs as Agents cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- SGVEF-LOOP: Coverage-Guided Progressive Topological Exploration and Fact-Grounded Metamorphic Evaluation for MCP Agents cites AgentBench: Evaluating LLMs as Agents
- SGVEF-LOOP: Coverage-Guided Progressive Topological Exploration and Fact-Grounded Metamorphic Evaluation for MCP Agents cites ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs cites Reflexion: language agents with verbal reinforcement learning
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Cited by top-tier papers3
- CoEvolve: Training LLM Agents via Agent-Data Mutual EvolutionShidong Yang, Ziyu Ma, Tongwen Huang, Yiming Hu et al.ACL 2026 · 6 citations
- ActionStudio: A Lightweight Framework for Data and Training of Large Action ModelsJianguo Zhang, Thai Hoang, Ming Zhu, Zuxin Liu et al.EMNLP 2025 · 1 citation
- SGVEF-LOOP: Coverage-Guided Progressive Topological Exploration and Fact-Grounded Metamorphic Evaluation for MCP AgentsZenghao Liu, Yansong ZhangACL 2026
Builds on8
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIsYujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu et al.ICLR 2024 · 1,469 citations
- WebArena: A Realistic Web Environment for Building Autonomous AgentsShuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou et al.ICLR 2024 · 1,197 citations
- AgentBench: Evaluating LLMs as AgentsXiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu et al.ICLR 2024 · 748 citations
Related papers
- Self-Challenging Language Model AgentsYifei Zhou, Sergey Levine, Jason E. Weston, Xian Li et al.NeurIPS 2025 · 52 citations
- LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied AgentsJae-Woo Choi, Youngwoo Yoon, Hyobin Ong, Jaehong Kim et al.ICLR 2024 · 49 citations
- GOAT: A Training Framework for Goal-Oriented Agent with ToolsHyunji Min, Sangwon Jung, Junyoung Sung, Dosung Lee et al.ACL Findings 2026
- Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based RewardsYuanjie Lyu, Chengyu Wang, Lei Shen, Jun Huang et al.ACL 2026 · 3 citations
- Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement LearningZhaoyang Wang, Canwen Xu, Boyi Liu, Yite Wang et al.ICML 2026 · 25 citations
