Metraipolis › archive › dc_b8cf5bdcbba0
ReGE: Stronger Agents through Experience Synthesis — arXiv:2610.33861
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.33861
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:57:25.455Z
- SHA-256 of the archived text
d6fcb19fdb94cb3927d3aef370015cb485aba22e41e8e05a1da6ac7c95005ecf- Stable URL of this page
https://metraipolis.com/documento/dc_b8cf5bdcbba0
How to cite
ReGE: Stronger Agents through Experience Synthesis — arXiv:2610.33861 — arXiv (en), https://arxiv.org/abs/2610.33861 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b8cf5bdcbba0 (Metraipolis archive dc_b8cf5bdcbba0, sha256 d6fcb19fdb94cb3927d3aef370015cb485aba22e41e8e05a1da6ac7c95005ecf)
BibTeX
@misc{dcb8cf5bdcbba0,
title = {ReGE: Stronger Agents through Experience Synthesis — arXiv:2610.33861},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.33861},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b8cf5bdcbba0; sha256 d6fcb19fdb94cb3927d3aef370015cb485aba22e41e8e05a1da6ac7c95005ecf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33861. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Repeated attempts at interactive tasks uncover facts, useful operations, and failures that can inform subsequent execution. We introduce ReGE, a framework for turning this recorded experience into guidance for a fresh attempt. Its main implementation, ReGE-Syn, uses a single coach call to jointly synthesize bounded execution records and available artifacts into self-contained guidance, connecting task-specific findings with proposed actions and relevant pitfalls. A student starts from the task's initial environment state and adapts this guidance to current observations. Source generation, synthesis, and student execution use the same base model, without parameter updates or a stronger teacher. Across four benchmarks, ReGE improves accuracy by an average of 9.9 percentage points for GPT and 8.8 percentage points for Claude compared with unguided execution. On matched BrowseComp-Plus subsets, ReGE-Syn reduces guidance-construction tokens by 98.2\% on GPT and 95.5\% on Claude relative to adapted AggAgent, with observed success. Combined construction and execution tokens decrease by 15.7\% and 35.4\%, respectively, counting input plus output and excluding source generation. BrowseComp-Plus ablations further associate access to process information with fewer student steps and show that joint synthesis produces substantially shorter guidance than Direct history or Independent summaries, with observed success. These results demonstrate how agents can use their own recorded experience to improve subsequent task completion, and suggest a low-cost way to consolidate the execution records of parallel agent systems such as agent swarms. 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/2610.33861 — 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 2026-10-27T07:55:30.674Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).