Metraipolis › archive › dc_a150d5f85387
Mosaic: Multi-Session Agentic Reinforcement Learning — arXiv:2610.22174
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22174
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:31:03.089Z
- SHA-256 of the archived text
5a35347fffef28a439e56d938ab887dde22d65414468a5dbf300476797e66861- Stable URL of this page
https://metraipolis.com/documento/dc_a150d5f85387
How to cite
Mosaic: Multi-Session Agentic Reinforcement Learning — arXiv:2610.22174 — arXiv (en), https://arxiv.org/abs/2610.22174 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a150d5f85387 (Metraipolis archive dc_a150d5f85387, sha256 5a35347fffef28a439e56d938ab887dde22d65414468a5dbf300476797e66861)
BibTeX
@misc{dca150d5f85387,
title = {Mosaic: Multi-Session Agentic Reinforcement Learning — arXiv:2610.22174},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22174},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a150d5f85387; sha256 5a35347fffef28a439e56d938ab887dde22d65414468a5dbf300476797e66861},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22174. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Most existing agentic reinforcement learning methods assume single-session trajectories, where interaction proceeds within one continuously accumulated context. However, agentic techniques such as context compaction and subagent forking may produce trajectories spanning multiple sessions, creating a mismatch between the single-session training assumption and inference-time execution. Therefore, we introduce Multi-Session Agentic Reinforcement Learning, a more general setting that supports an arbitrary number of sessions within a trajectory. Under this setting, a widely adopted method is to broadcast trajectory-level advantages to all sessions, but this does not distinguish contributions from various sessions or guide session allocation within trajectories. To address this issue, we propose Mosaic, a multi-session agentic RL method with critic-free hierarchical optimization. At the trajectory level, it incorporates session-usage signals into advantage estimation. At the session level, it shapes each session's advantage according to the estimated marginal contribution. Experiments on BrowseComp with Qwen3.5-4B show that Mosaic outperforms broadcasting in both context compaction and subagent forking scenarios while using fewer sessions on average. Further analyses show that our method achieves improvements in session utility and allocation, which we suggested is a promising target for future advances in multi-session agentic RL. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.22174 — 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 2026-10-16T08:44:18.033Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).