Metraipolis › archive › dc_e5810bfef97e
Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents — arXiv:2610.10179
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10179
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:11:49.832Z
- SHA-256 of the archived text
d43910d283f065b60947c85bf5c32c187a8dd87c48980570c4372b507bf1b69f- Stable URL of this page
https://metraipolis.com/documento/dc_e5810bfef97e
How to cite
Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents — arXiv:2610.10179 — arXiv (en), https://arxiv.org/abs/2610.10179 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e5810bfef97e (Metraipolis archive dc_e5810bfef97e, sha256 d43910d283f065b60947c85bf5c32c187a8dd87c48980570c4372b507bf1b69f)
BibTeX
@misc{dce5810bfef97e,
title = {Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents — arXiv:2610.10179},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10179},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e5810bfef97e; sha256 d43910d283f065b60947c85bf5c32c187a8dd87c48980570c4372b507bf1b69f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10179. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Search agents enable Large Language Models (LLMs) to iteratively retrieve and use information for complex multi-hop questions. Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising approach for post-training such agents, but its reliance on sparse, outcome-based supervision can make credit assignment difficult and limit learning efficiency. In this paper, we systematically investigate how intermediate supervision can improve reinforcement learning for search agents. We study a range of reward-shaping and credit-assignment strategies that provide learning signals from intermediate retrieval steps. Building on these insights, we develop a training framework that combines intermediate signals with final outcome rewards to improve learning from multi-step search trajectories. Experiments across multiple benchmarks under matched training conditions demonstrate improvements in aggregate search-agent performance and show that both the choice of intermediate signal and where its credit is assigned affect training behaviour. These findings show that reward design and credit assignment are important design dimensions for training effective search agents. 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/2610.10179 — 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 2026-10-08T10:14:06.157Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).