# BRIDGE: Selective Boundary Repair with Dependency Graph Evidence in Multi-Agent Systems

arXiv: https://arxiv.org/abs/2610.17805 · HTML: https://mlsanity.com/paper/2610.17805/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 20 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 20 of 20)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.00212/) (2025)
- [Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2410.02506/) (2024)
- [G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems](https://mlsanity.com/paper/2506.07398/) (2025)
- [Agent-Oriented Planning in Multi-Agent Systems](https://mlsanity.com/paper/2410.02189/) (2024)
- [Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems](https://mlsanity.com/paper/2603.01045/) (2026)
- [MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2602.19843/) (2026)
- [AgentAsk: Multi-Agent Systems Need to Ask](https://mlsanity.com/paper/2510.07593/) (2025)
- [Verification-Aware Planning for Multi-Agent Systems](https://mlsanity.com/paper/2510.17109/) (2025)
- [TeamBench: Evaluating Agent Coordination under Enforced Role Separation](https://mlsanity.com/paper/2605.07073/) (2026)
- [MOC: Multi-Order Communication in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2606.02359/) (2026)
- [S3Mem: Structured Spatiotemporal Scene-Event Memory for Long-Horizon Interactive Question Answering](https://mlsanity.com/paper/2605.28831/) (2026)
- [Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation](https://mlsanity.com/paper/2608.25277/) (2026)

## Abstract (arXiv)

Multi-agent collaboration has emerged as a critical paradigm for tackling complex, long-horizon tasks; however, while coordination protocols continue to advance, systemic failures at the inter-agent collaboration interface remain a pervasive bottleneck. In collaborative workflows, systems frequently suffer from broken handoffs---where critical task context is omitted, misrouted, or ignored despite each agent emitting locally plausible responses. To address this challenge, we present method, a verifiable runtime control framework that treats handoff repair as selective intervention over explicit dependency graphs. Central to method is an integrated fault-attribution and calibration pipeline, dataset, which decouples execution dependencies and injects counterfactual handoff perturbations to provide empirical supervision for runtime intervention. Leveraging this diagnostic foundation, method dynamically compiles observable interaction traces into a provenance graph to pinpoint unresolved dependencies, without accessing private agent states. It then evaluates candidate repairs through an empirical gate that weighs expected gains against disruption risks, and executes repairs only when formal local postconditions hold. Extensive evaluations across demanding benchmarks demonstrate that method boosts task success by up to 12.3 absolute percentage points on SILO-BENCH and 11.1 on TeamBench. Across both backbones, method maintains strict cost-effectiveness, adding as little as 2.0% marginal token overhead. Furthermore, on 562 handoff-relevant traces from the MAST benchmark, method achieves 69.8% F1 in a single pass, establishing a reliable operational boundary for verifiable coordination repair.