Metraipolis › archive › dc_d702a24d678e

Reward Engine: Reward-Centric Self-Evolution for Open-Ended Tool Agents — arXiv:2610.22915

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22915
License (as archived)
CC0-1.0
Archived
2026-10-19T08:42:19.711Z
SHA-256 of the archived text
59f850dba1ad56bf1dd812589c65120fbb811f11f8df5e384d6100ef7847bb0d
Stable URL of this page
https://metraipolis.com/documento/dc_d702a24d678e

How to cite

Reward Engine: Reward-Centric Self-Evolution for Open-Ended Tool Agents — arXiv:2610.22915 — arXiv (en), https://arxiv.org/abs/2610.22915 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d702a24d678e (Metraipolis archive dc_d702a24d678e, sha256 59f850dba1ad56bf1dd812589c65120fbb811f11f8df5e384d6100ef7847bb0d)
BibTeX
@misc{dcd702a24d678e,
  title = {Reward Engine: Reward-Centric Self-Evolution for Open-Ended Tool Agents — arXiv:2610.22915},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22915},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d702a24d678e; sha256 59f850dba1ad56bf1dd812589c65120fbb811f11f8df5e384d6100ef7847bb0d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22915. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Open-ended tool agents can complete the same objective through different tool paths, and their quality depends jointly on the interaction trace, environment state, and final artifacts, so such tasks rarely admit an executable ground-truth reward. The central challenge is therefore to construct a reward from existing experience that exposes the current policy's failures while remaining stationary during optimization. We introduce Reward Engine, which, like a self-motivated student, first works out what success requires and then optimizes toward it. From the task and initial trajectories, it builds a RewardPack of testcases for required correctness and rubrics for graded quality, each executed as a check that returns a judgment with evidence. The frozen RewardPack then guides the agent to revise and select its outputs, and can also serve as a reward for reinforcement learning. On WorkBuddy Bench Office and Claw-Eval, the constructed reward largely agrees with the benchmark graders, not reversing their ordering on 82.3\% and 80.5\% of candidate pairs. Used to revise executions, it raises three-run consistency ($\mathrm{Pass}^{3}$) over Baseline from 45.0\% to 54.0\% and from 78.4\% to 83.7\%.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.22915 — 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 2026-10-19T08:39:10.045Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).