Search papers, labs, and topics across Lattice.
The Atomic Task Graph (ATG) framework enhances the planning and execution capabilities of LLM-based agents by explicitly modeling task dependencies as directed acyclic graphs (DAGs). This approach allows for the parallel execution of independent subtasks and facilitates error localization and repair, significantly improving both success rates and execution efficiency without the need for larger models or extensive fine-tuning. Experiments demonstrate that ATG outperforms existing methods across multiple benchmarks using relatively small backbone models (7B-8B parameters).
By exposing task dependencies through a graph structure, ATG enables LLMs to execute complex tasks more efficiently and reliably than ever before.
LLM-based agents have shown strong potential for solving complex multi-step tasks, yet existing performance improvements often rely on either scaling to larger backbone models or task-specific fine-tuning. The former incurs substantial computational costs, while the latter typically generalizes poorly across different tasks. Although prompt-based control is training-free and broadly applicable, existing methods still leave input-output dependencies between subtasks implicit in textual trajectories, making verified intermediate results difficult to reuse. To address these limitations, we propose Atomic Task Graph (ATG), a unified control framework for planning and execution. Specifically, ATG maintains an explicit graph to expose dependencies and support reuse. During planning, it recursively decomposes a high-level task into subtasks, forming a sequence of directed acyclic graphs (DAGs) whose evolution can be traced. During execution, the dependencies exposed by ATG allow independent branches to be executed in parallel, thereby improving execution efficiency. When failures are detected, ATG leverages the graph evolution history to localize the error source and repair only the affected region, preserving validated regions unchanged. Experiments show that ATG consistently outperforms strong baselines in success rate and execution efficiency across three interactive benchmarks using only 7B-8B backbones.
