{"ID":2848949,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.24126","arxiv_id":"2510.24126","title":"Reinforcement Learning for Long-Horizon Multi-Turn Search Agents","abstract":"Large Language Model (LLM) agents can leverage multiple turns and tools to solve complex tasks, with prompt-based approaches achieving strong performance. This work demonstrates that Reinforcement Learning (RL) can push capabilities significantly further by learning from experience. Through experiments on a legal document search benchmark, we show that our RL-trained 14 Billion parameter model outperforms frontier class models (85% vs 78% accuracy). In addition, we explore turn-restricted regimes, during training and at test-time, that show these agents achieve better results if allowed to operate over longer multi-turn horizons.","short_abstract":"Large Language Model (LLM) agents can leverage multiple turns and tools to solve complex tasks, with prompt-based approaches achieving strong performance. This work demonstrates that Reinforcement Learning (RL) can push capabilities significantly further by learning from experience. Through experiments on a legal docum...","url_abs":"https://arxiv.org/abs/2510.24126","url_pdf":"https://arxiv.org/pdf/2510.24126v1","authors":"[\"Vivek Kalyan\",\"Martin Andrews\"]","published":"2025-10-28T07:00:42Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\"]","has_code":false}