Metraipolis › archive › dc_a0dbaa162c2d
From Uncertainty to Action: Learning to Steer LLM Agents — arXiv:2610.09115
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09115
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:08:56.692Z
- SHA-256 of the archived text
6bec00156a1ef029709d6c48853adfa0bed73aa5eae119a63b788d6ac638c499- Stable URL of this page
https://metraipolis.com/documento/dc_a0dbaa162c2d
How to cite
From Uncertainty to Action: Learning to Steer LLM Agents — arXiv:2610.09115 — arXiv (en), https://arxiv.org/abs/2610.09115 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a0dbaa162c2d (Metraipolis archive dc_a0dbaa162c2d, sha256 6bec00156a1ef029709d6c48853adfa0bed73aa5eae119a63b788d6ac638c499)
BibTeX
@misc{dca0dbaa162c2d,
title = {From Uncertainty to Action: Learning to Steer LLM Agents — arXiv:2610.09115},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09115},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a0dbaa162c2d; sha256 6bec00156a1ef029709d6c48853adfa0bed73aa5eae119a63b788d6ac638c499},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09115. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Steering an LLM agent means deciding whether to correct it, at which step, and with which mechanism. Uncertainty is often used to decide when to correct an agent, but whether it can guide these decisions remains unclear. We steer agent trajectories separately at every non-terminal step with each of four mechanisms and run each continuation to completion. The resulting stepwise outcome table (SOT) holds about 82,000 counterfactual continuations of 1,864 trajectories from three benchmarks and two agents. It shows that uncertainty can identify failing trajectories, but that no single signal reliably locates the step at which steering helps. We therefore propose VoS (Value of Steering), a trajectory-level monitor, offline or online, that learns from SOT the value of steering at each step and decides where to steer by it. A harm-budgeted trigger decides whether to steer, limiting the fraction of successful trajectories that VoS disturbs. VoS improves on unmodified execution in all 12 settings of benchmark, agent, and offline or online use, by 7.8 points on average, and outperforms the strongest of five existing uncertainty-triggered methods in 11, by 2.9 points on average. Ablations show that training on measured outcomes and a tight harm budget are both essential. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.09115 — 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 2026-10-08T10:14:05.903Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).