Metraipolis › archive › dc_fe19fa1ab304

EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning — arXiv:2609.35290

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35290
License (as archived)
CC0-1.0
Archived
2026-10-07T20:58:40.453Z
SHA-256 of the archived text
d1472487906a21133b77e1fc0111c5221a8953c221f93c7e83a9b34a2c0d8947
Stable URL of this page
https://metraipolis.com/documento/dc_fe19fa1ab304

How to cite

EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning — arXiv:2609.35290 — arXiv (en), https://arxiv.org/abs/2609.35290 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe19fa1ab304 (Metraipolis archive dc_fe19fa1ab304, sha256 d1472487906a21133b77e1fc0111c5221a8953c221f93c7e83a9b34a2c0d8947)
BibTeX
@misc{dcfe19fa1ab304,
  title = {EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning — arXiv:2609.35290},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35290},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe19fa1ab304; sha256 d1472487906a21133b77e1fc0111c5221a8953c221f93c7e83a9b34a2c0d8947},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35290. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent work has explored improving agents by jointly evolving their harnesses and models, but often takes a ''potpourri'' approach that bundles together new tools, new decision-making procedures, and model adaptation to the evolved harness under a single notion of agent improvement. In this paper, we instead investigate how agents can improve their decision-making procedures. In particular, we propose EvoIn, an agent fine-tuning framework that bridges evolution and internalization. EvoIn first analyzes agent execution traces to evolve and validate new decision-making procedures by temporarily instantiating them in the harness. The validated procedures guide the agent to generate improved reasoning traces. These traces are then rewritten into self-contained reasoning traces, removing explicit references to harness instructions while expressing the induced decision logic as the model's own reasoning. Finally, EvoIn fine-tunes the model on the rewritten traces, internalizing these procedures so that the improved decision-making persists without the evolved harness at inference time. We evaluate EvoIn on diverse benchmarks and find that it consistently enables agents to learn stronger decision-making procedures, raising the pass rate by 10.9 points in-domain and by 9.2 points out-of-domain. Results further show that the internalized decision procedures generalize to unseen tasks. Case studies show that agents can learn to decide how to solve a task before solving it, for example by checking a document's length to choose between reading it in full and searching it. EvoIn is also broadly applicable, showing consistent improvements on another model family.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.35290 — 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 2026-10-07T20:29:01.824Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).