cs.MANov 11, 2026

MULTILOOP: Evolving Multi-Agent Harnesses for Complex Information-Seeking Tasks

Authors: Daniela Gottesman, Gal Yona, Ori Ram, Zorik Gekhman, Jonathan Herzig, Mor Geva, Roee Aharoni

Organizations: Tel Aviv University · Google Research

Abstract

The performance of LLM-based agents depends not only on the underlying model but also on the harness: the prompts, tools, and orchestration logic around it. Recent works automate harness optimization with coding agents that analyze execution traces, diagnose failures, and edit the harness code; however, those focused on single-agent systems. Multi-agent harnesses are harder to optimize as fixing them requires changing how agents interact in addition to how each behaves. We study whether automated harness optimization can diagnose and repair failures in multi-agent systems through a case study on complex information-seeking tasks from DeepSearchQA [Gupta et al., 2026]. We apply MULTILOOP, a simple optimization loop in which a coding agent iteratively analyzes, evaluates and edits the harness. With only 10 training samples, the evolved harness improves accuracy by 4.6% over the base harness and by 3.2% over the best single-agent system. However, a taxonomy of failure modes before and after optimization shows that the orchestration failures that characterize multi-agent systems largely persist. Our findings motivate harness optimization methods that encourage structural changes to how agents delegate tasks and share information.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. HarnessFlow: MCTS-Guided Harness Optimization for LLM Agents

    Nov 4, 2026Zhi Hong, Qianlong Wang, Hongchen Wei +5Agent Harness OptimizationLLM Agent Harnesses

  2. MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution

    Sep 29, 2026Prithwish Jana, Mononito Goswami, Hao Liu +9Multi-Agent OrchestrationEvolutionary Optimization