Metraipolis › archive › dc_eb54ec7e5de9
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents — arXiv:2608.26530
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26530
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T14:22:40.675Z
- SHA-256 of the archived text
23be3e31465737a0361bae5e098534cb6e92e856f079f4bf9351c625aaf8d7a2- Stable URL of this page
https://metraipolis.com/documento/dc_eb54ec7e5de9
How to cite
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents — arXiv:2608.26530 — arXiv (en), https://arxiv.org/abs/2608.26530 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb54ec7e5de9 (Metraipolis archive dc_eb54ec7e5de9, sha256 23be3e31465737a0361bae5e098534cb6e92e856f079f4bf9351c625aaf8d7a2)
BibTeX
@misc{dceb54ec7e5de9,
title = {PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents — arXiv:2608.26530},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26530},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb54ec7e5de9; sha256 23be3e31465737a0361bae5e098534cb6e92e856f079f4bf9351c625aaf8d7a2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26530. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience only after execution ends, so they cannot redirect the active run or immediately apply and validate lessons learned from it. We argue that self-improvement should instead be live, using emerging experience both to redirect the active run and to update the persistent harness. Existing agent architectures do not fully support this goal. Single-agent self-correction combines task execution and trajectory assessment within one context, while subagent delegation separates execution but typically cannot redirect an active subagent. We present PILOT, a supervisor-worker harness for live self-improvement through two coupled mechanisms: (1) live steering lets a separate supervisor redirect or abort the active worker during execution; and (2) live self-evolution distils procedures and failure modes revealed during execution into reusable skills and memory. Across two frozen backbones and three benchmarks, PILOT ranks first in five of six configurations. On Terminal-Bench 2.0, PILOT outperforms counterpart harnesses by up to 9.8 percentage points. In the self-improvement setting, PILOT gains 14.6 points with GLM-5.1 and 12.4 points with Kimi-K2.6. Mean output tokens fall by 42.9% and 47.4%, while successful evaluations per million output tokens rise by 110.3% and 134.0%, respectively. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.26530 — 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 2026-10-17T13:16:53.498Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).