Metraipolis › archive › dc_aabb848051dd
Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context Reinforcement Learning — arXiv:2610.11152
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11152
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:13:44.240Z
- SHA-256 of the archived text
615ab5befd0372b01cfeea10f1eaa9ce6679aebf04704880cb2275fe6bde9df5- Stable URL of this page
https://metraipolis.com/documento/dc_aabb848051dd
How to cite
Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context Reinforcement Learning — arXiv:2610.11152 — arXiv (en), https://arxiv.org/abs/2610.11152 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aabb848051dd (Metraipolis archive dc_aabb848051dd, sha256 615ab5befd0372b01cfeea10f1eaa9ce6679aebf04704880cb2275fe6bde9df5)
BibTeX
@misc{dcaabb848051dd,
title = {Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context Reinforcement Learning — arXiv:2610.11152},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11152},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aabb848051dd; sha256 615ab5befd0372b01cfeea10f1eaa9ce6679aebf04704880cb2275fe6bde9df5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11152. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM agents increasingly improve at inference time by accumulating experience in context rather than by updating parameters. This process is often described as in-context reinforcement learning (ICRL). Whether in-context learning (ICL) can actually play the role of RL, however, has not been tested. We study this question in its simplest form, direct ICRL, where the model conditions directly on raw trajectory-reward pairs, and ask whether the reward acts as a learning signal. Through controlled experiments on four benchmarks across six models, we find that the reward is read, but its effect is small: flipping, randomizing, or removing the reward leaves the improvement curve almost unchanged, and this holds even under meta-prompts that explicitly instruct the model to explore, exploit, or reason over rewards. Trajectories drive improvement, but not through their semantic content: shuffled or corrupted trajectories work as well as real ones. These patterns closely mirror those known in ICL, suggesting that direct ICRL is better understood as a special case of ICL than as inference-time RL. This reframing has implications for agent memory design: ICL factors such as input distribution and demonstrations may matter more than RL elements such as reward shaping and exploration. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.11152 — 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 2026-10-09T05:47:15.417Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).