English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Laser: Governing Long-Horizon Agentic Search via Structured Protocol and Context Register

Forum topic · 小凯 · 2026-07-05

Summary

Laser (arXiv:2512.20458) is a framework for stabilizing and scaling agentic search systems built on LLMs and Large Reasoning Models. Existing agentic frameworks rely on unstructured natural-language reasoning and accumulate raw intermediate traces in context, causing unstable reasoning trajectories, context overflow, and degraded performance on multi-hop queries. Laser addresses this with two core components: (1) a symbolic action protocol that organizes agent behaviors into three spaces — planning, task-solving, and retrospection — where each action has explicit semantics and a deterministic execution format, making decisions interpretable, traceable, and reliably parseable; and (2) a compact context register that stores only essential reasoning states, enabling long-horizon reasoning without uncontrolled context expansion. Experiments on Qwen2.5/3-series models across challenging multi-hop QA datasets show Laser consistently outperforms existing agentic search baselines under both prompting-only and fine-tuning settings, providing a principled foundation for robust, scalable agentic search. The work is relevant to research on retrieval-augmented generation, tool-using agents, and industrial search systems.

Laser: Governing Long-Horizon Agentic Search via Structured Protocol and Context Register

Paper: arXiv:2512.20458 · Published: 2025-12-23 · Category: Agentic Search

Overview

This post summarizes the Laser framework, proposed for stabilizing and scaling long-horizon agentic search in LLM-based systems.

Background

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
  • Degraded performance on complex multi-hop queries
  • Key Ideas

    Laser consists of two coordinated components:

    1. Symbolic action protocol — 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 reasoning and reliable action parsing. Intermediate decisions become interpretable and traceable, supporting explicit retrospection and fine-grained control over reasoning trajectories.

    2. Compact context register — Stores only the essential states of the reasoning process, allowing the agent to reason over long horizons without uncontrolled context expansion.

    Results

    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.

    Original 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.

    Implications for Search and RAG Systems

  • Architecture: Agentic paradigms are making retrieval count and strategy learnable objects, beyond fixed cascade pipelines.
  • Evaluation: Process-level metrics (task success, citation accuracy, multi-hop chain completeness) complement static nDCG.
  • Engineering: Latency, cost, interpretability, and safety remain hard constraints for production deployment; readers should verify quantitative results against the original PDF tables.
  • Related Entries

  • Agentic Information Retrieval (arXiv:2410.09713)
  • Synergizing RAG and Reasoning: A Systematic Review
  • AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforcement Learning

Tags

#agentic-search#llm#rag#multi-hop-qa#reasoning#context-management#qwen#information-retrieval

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208473