Metraipolis › archive › dc_faf778c34b68
MULTILOOP: Evolving Multi-Agent Harnesses for Complex Information-Seeking Tasks — arXiv:2611.15754
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.15754
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-14T01:51:49.450Z
- SHA-256 of the archived text
b1e06c6f5f32ec380d713544adffbbb4f1d47ef84d5f0bf531c32b4266cd58de- Stable URL of this page
https://metraipolis.com/documento/dc_faf778c34b68
How to cite
MULTILOOP: Evolving Multi-Agent Harnesses for Complex Information-Seeking Tasks — arXiv:2611.15754 — arXiv (en), https://arxiv.org/abs/2611.15754 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_faf778c34b68 (Metraipolis archive dc_faf778c34b68, sha256 b1e06c6f5f32ec380d713544adffbbb4f1d47ef84d5f0bf531c32b4266cd58de)
BibTeX
@misc{dcfaf778c34b68,
title = {MULTILOOP: Evolving Multi-Agent Harnesses for Complex Information-Seeking Tasks — arXiv:2611.15754},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.15754},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_faf778c34b68; sha256 b1e06c6f5f32ec380d713544adffbbb4f1d47ef84d5f0bf531c32b4266cd58de},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.15754. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2611.15754 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-14T01:51:48.362Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).