AIBullisharXiv – CS AI · 10h ago7/10
🧠
CoCoDA: Co-evolving Compositional DAG for Tool-Augmented Agents
CoCoDA is a novel framework that enables smaller language models to efficiently use large tool libraries by organizing tools as a compositional DAG structure with typed signatures and specifications. The system co-evolves the planner and tool library during training, allowing an 8B model to match or exceed a 32B model's performance on mathematical and coding benchmarks while maintaining sublinear retrieval costs.