Metraipolis › archive › dc_fedf48a0ce0a

MOAE: Multi-Objective Agent Evolution with Pareto-Preserving Search — arXiv:2609.05992

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05992
License (as archived)
CC0-1.0
Archived
2026-10-16T13:58:47.782Z
SHA-256 of the archived text
7db35d21f080e227423bfbee06b28871fc20f2f34fe5cc41e45c0df14172616f
Stable URL of this page
https://metraipolis.com/documento/dc_fedf48a0ce0a

How to cite

MOAE: Multi-Objective Agent Evolution with Pareto-Preserving Search — arXiv:2609.05992 — arXiv (en), https://arxiv.org/abs/2609.05992 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fedf48a0ce0a (Metraipolis archive dc_fedf48a0ce0a, sha256 7db35d21f080e227423bfbee06b28871fc20f2f34fe5cc41e45c0df14172616f)
BibTeX
@misc{dcfedf48a0ce0a,
  title = {MOAE: Multi-Objective Agent Evolution with Pareto-Preserving Search — arXiv:2609.05992},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05992},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fedf48a0ce0a; sha256 7db35d21f080e227423bfbee06b28871fc20f2f34fe5cc41e45c0df14172616f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05992. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As LLM-based agents continue to advance, their evaluation has become increasingly multifaceted: a capable agent must not only achieve high task completion accuracy but also perform well in interaction quality, safety, and efficiency, raising a central question: can these objectives be optimized simultaneously? Existing methods have considered multiple objectives, but many collapse heterogeneous measurements into a fixed scalar score. Such scalarization depends on metric normalization and preference weights and may discard candidates that represent useful deployment trade-offs. We introduce Multi-Objective Agent Evolution (MOAE), which organizes iterative in-context refinement as a Pareto-preserving evolutionary search over complete agent rollouts. Given a limited rollout budget, MOAE maintains an empirical archive of non-dominated candidates, uses objective-specific diagnostics to guide offspring generation, and applies constraint-aware selection only at deployment. This separates candidate preservation during search from the preference used to return a final solution. The procedure requires no parameter updates and allows each objective to be replaced by any measurable property, which we instantiate as task performance, trajectory quality, and safety. Experiments on TravelPlanner and AgentDojo show that MOAE consistently improves task performance and trajectory quality while maintaining strong safety under matched rollout budgets. Search-behavior analysis further shows that Pareto preservation expands the attainable objective region and increases the frequency of joint improvement. These results demonstrate the potential of Pareto-preserving in-context evolution for optimizing multiple agent properties without committing to a fixed scalarization during search.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.05992 — 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 2026-10-16T13:39:43.140Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).