{"ID":2825885,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20458","arxiv_id":"2512.20458","title":"Laser: Governing Long-Horizon Agentic Search via Structured Protocol and Context Register","abstract":"Recent advances in Large Language Models (LLMs) and Large Reasoning Models (LRMs) have enabled agentic search systems that interleave multi-step reasoning with external tool use. However, existing frameworks largely rely on unstructured natural-language reasoning and accumulate raw intermediate traces in the context, which often leads to unstable reasoning trajectories, context overflow, and degraded performance on complex multi-hop queries. In this study, we introduce Laser, a general framework for stabilizing and scaling agentic search. Laser defines a symbolic action protocol that organizes agent behaviors into three spaces: planning, task-solving, and retrospection. Each action is specified with explicit semantics and a deterministic execution format, enabling structured and logical reasoning processes and reliable action parsing. This design makes intermediate decisions interpretable and traceable, enhancing explicit retrospection and fine-grained control over reasoning trajectories. In coordination with parsable actions, Laser further maintains a compact context register that stores only essential states of the reasoning process, allowing the agent to reason over long horizons without uncontrolled context expansion. Experiments on Qwen2.5/3-series models across challenging multi-hop QA datasets show that Laser consistently outperforms existing agentic search baselines under both prompting-only and fine-tuning settings, demonstrating that Laser provides a principled and effective foundation for robust, scalable agentic search.","short_abstract":"Recent advances in Large Language Models (LLMs) and Large Reasoning Models (LRMs) have enabled agentic search systems that interleave multi-step reasoning with external tool use. However, existing frameworks largely rely on unstructured natural-language reasoning and accumulate raw intermediate traces in the context, w...","url_abs":"https://arxiv.org/abs/2512.20458","url_pdf":"https://arxiv.org/pdf/2512.20458v2","authors":"[\"Shuting Wang\",\"Qiaolin Xia\",\"Vich Wang\",\"Herberttli\",\"Bobsimons\",\"Zhicheng Dou\"]","published":"2025-12-23T15:53:33Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[\"Large Language Model\",\"Language Model\",\"Generative Adversarial Network\"]","has_code":false}