Metraipolis › archive › dc_289875c58dce

ConflictGuide: AutoResearch Improves When Competing Behaviors Are Made Visible — arXiv:2609.39933

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39933
License (as archived)
CC0-1.0
Archived
2026-10-07T12:43:01.801Z
SHA-256 of the archived text
99a6bff974886b1f655c4bf48f5d22416d089d1530ba9b5ab12e87e84e0debda
Stable URL of this page
https://metraipolis.com/documento/dc_289875c58dce

How to cite

ConflictGuide: AutoResearch Improves When Competing Behaviors Are Made Visible — arXiv:2609.39933 — arXiv (en), https://arxiv.org/abs/2609.39933 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_289875c58dce (Metraipolis archive dc_289875c58dce, sha256 99a6bff974886b1f655c4bf48f5d22416d089d1530ba9b5ab12e87e84e0debda)
BibTeX
@misc{dc289875c58dce,
  title = {ConflictGuide: AutoResearch Improves When Competing Behaviors Are Made Visible — arXiv:2609.39933},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39933},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_289875c58dce; sha256 99a6bff974886b1f655c4bf48f5d22416d089d1530ba9b5ab12e87e84e0debda},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39933. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When designing machine learning models, desirable properties are often in tension: improving one behavior can impair another, so task progress can depend on alleviating the conflict. LLM-based AutoResearch systems, which iteratively edit model code and retain edits based on scalar task-performance feedback, have largely ignored this trade-off. We find that scalar feedback supports broad exploration early in search, but it does not reveal how edits affect competing behaviors. In matched-budget experiments, introducing competing-behavior feedback as task gains diminish increases the share of proposals that improve both behaviors and sustains progress beyond scalar-only plateaus. Obtaining this feedback for a given model requires identifying its competing behaviors and designing probes to measure them. To make competing-behavior feedback actionable, we introduce ConflictGuide. Its reusable ConflictGuide-Skill combines a literature-grounded taxonomy with model-specific evidence to identify competing behaviors and specify probes for a code agent to implement as metrics. Evolution proceeds in two stages: Stage I explores with task feedback; Stage II uses probe feedback to steer proposals toward conflict alleviation and retains marginal-gain edits only when probes indicate sufficient alleviation. Across five diverse model families, ConflictGuide reduces task and conflict-related errors by up to 28% and 14%, respectively, relative to scalar-only AutoResearch, with gains extending to other code agents.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.39933 — 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 2026-10-07T12:14:13.800Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).