LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback
This addresses the data scarcity problem for researchers and developers training AI agents on multi-step tasks, though it is incremental as it builds on existing agentic benchmarks and methods.
The paper tackles the challenge of generating high-quality training data for Large Action Models (LAMs) in AI agents by introducing LAM SIMULATOR, a framework for online exploration and trajectory feedback, resulting in models that achieve up to a 49.3% performance improvement over baselines on benchmarks like ToolBench and CRMArena.
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 real-time 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 high-quality training datasets for LAMs. Our experiments on popular agentic benchmarks, ToolBench 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.