Skip to content
Book Open access

LaMAR: Latent Multi-agent Collaboration via KV-Cache Communication for Automated Program Repair

Oct 2026 · Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering · 0 citations · 49 references

Abstract

Multi-agent systems for automated program repair communicate through text tokens, requiring each agent to decode its internal state into discrete symbols and the next agent to re-encode them. This conversion loses information and incurs token overhead that grows quadratically with the agent count. We develop Latent Agent Communication (LAC), a theoretically grounded framework that formalizes how agents can share KV-cache representations directly in continuous space, and prove it provides a communication channel with strictly higher information capacity while reducing token complexity from O(N^2) to O(N). We instantiate LAC as LaMAR, a dual-chain repair system: Bug Analysis Chain diagnoses the bug through four collaborating latent agents; Repair Chain refines the patch through multi-agent latent collaboration with cross-chain context transfer, and supports optional multi-round iteration for complex defects. Evaluated across three benchmarks spanning Java, Python, and C++ with three model families, LaMAR with Qwen3-8B achieves 24.5% repair success rate on Defects4J and 62.1%--87.5% on DebugBench and QuixBugs, outperforming all baselines in the large majority of settings. Ablation experiments identify the bug analysis chain and latent communication as the most critical components.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.