CoCoDA: Co-evolving Compositional DAG for Tool-Augmented Agents

TL;DR

CoCoDA introduces a co-evolving, compositional DAG framework for tool-augmented language models, enabling efficient retrieval, structured tool management, and improved reasoning performance.

Contribution

It presents a novel code-native DAG structure for joint evolution of planner and tool library, reducing retrieval costs and enhancing compositional reasoning.

Findings

Achieves performance comparable to larger models on GSM8K and MATH benchmarks.

Reduces retrieval cost and time through symbolic signature unification.

Improves over existing tool-use baselines in various reasoning tasks.

Abstract

Tool-augmented language models can extend small language models with external executable skills, but scaling the tool library creates a coupled challenge: the library must evolve with the planner as new reusable subroutines emerge, while retrieval from the growing library must remain within a fixed context budget. Existing tool-use and skill-library methods typically treat tools as flat or text-indexed memories, causing prompt cost to grow with library size and obscuring the typed, compositional structure of executable code. We propose CoCoDA, a framework that co-evolves the planner and tool library through a single code-native structure: a compositional code DAG. Nodes are primitive or composite tools, edges encode invocation dependencies, and each node stores a typed signature, description, pre/post-condition specification, and worked examples. At inference time, Typed DAG Retrieval prunes candidates by symbolic signature unification, ranks survivors by descriptions, filters them by behavioral specifications, and disambiguates with examples, keeping expensive context materialization on progressively smaller candidate sets. At training time, successful trajectories are folded into validated composite tools, while the planner is updated with a DAG-induced reward that credits composites by their primitive expansion size. We provide theoretical results showing retrieval cost reduction, sublinear retrieval time, compositional advantage under the shaped reward, monotone co-evolution under conservative updates, and DAG well-formedness. Across mathematical reasoning, tabular analysis, and code task benchmarks, CoCoDA enables an 8B student to match or exceed a 32B teacher on GSM8K and MATH and consistently improves over strong tool-use and library-learning baselines.