SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Yuyang, Qian, Hongjin, Wang, Shuting, Liu, Jiongnan, Zhao, Ziliang, Tan, Jiejun, Liu, Zheng, Dou, Zhicheng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917527748083712
author Hu, Yuyang
Qian, Hongjin
Wang, Shuting
Liu, Jiongnan
Zhao, Ziliang
Tan, Jiejun
Liu, Zheng
Dou, Zhicheng
author_facet Hu, Yuyang
Qian, Hongjin
Wang, Shuting
Liu, Jiongnan
Zhao, Ziliang
Tan, Jiejun
Liu, Zheng
Dou, Zhicheng
contents Long-horizon agentic reasoning requires large language models to act over long interaction histories containing thoughts, tool calls, observations, and partial conclusions. The challenge is not merely that these histories grow long, but that information needed for the current decision may be scattered across distant steps and only become relevant later. Existing approaches address this difficulty by truncating the interaction history, compressing it into shorter surrogates, or retrieving selected parts of it for reuse, but they do not explicitly model how access to past interaction should adapt to the agent's evolving state. We instead cast long-horizon reasoning as a problem of state-adaptive memory. To this end, we propose State-Adaptive Memory~(SAM), a standalone framework that consolidates ongoing interaction into compact memory cues while preserving raw trajectory pages for intent-driven recall. These cues are not treated as replacements for history; rather, they serve as lightweight handles that allow the agent to reconstruct temporally distant information according to its current needs, without retraining the underlying backbone. We further optimize the memory module through expert-guided supervision and reinforcement learning, aligning it with trajectory-level utility. Across BrowseComp, BrowseComp-ZH, WideSearch, and HLE, SAM consistently outperforms strong baselines over diverse agent backbones. Our results suggest that explicit memory modeling provides a simple and effective foundation for long-horizon agentic reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2605_24468
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
Hu, Yuyang
Qian, Hongjin
Wang, Shuting
Liu, Jiongnan
Zhao, Ziliang
Tan, Jiejun
Liu, Zheng
Dou, Zhicheng
Artificial Intelligence
Long-horizon agentic reasoning requires large language models to act over long interaction histories containing thoughts, tool calls, observations, and partial conclusions. The challenge is not merely that these histories grow long, but that information needed for the current decision may be scattered across distant steps and only become relevant later. Existing approaches address this difficulty by truncating the interaction history, compressing it into shorter surrogates, or retrieving selected parts of it for reuse, but they do not explicitly model how access to past interaction should adapt to the agent's evolving state. We instead cast long-horizon reasoning as a problem of state-adaptive memory. To this end, we propose State-Adaptive Memory~(SAM), a standalone framework that consolidates ongoing interaction into compact memory cues while preserving raw trajectory pages for intent-driven recall. These cues are not treated as replacements for history; rather, they serve as lightweight handles that allow the agent to reconstruct temporally distant information according to its current needs, without retraining the underlying backbone. We further optimize the memory module through expert-guided supervision and reinforcement learning, aligning it with trajectory-level utility. Across BrowseComp, BrowseComp-ZH, WideSearch, and HLE, SAM consistently outperforms strong baselines over diverse agent backbones. Our results suggest that explicit memory modeling provides a simple and effective foundation for long-horizon agentic reasoning.
title SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
topic Artificial Intelligence
url https://arxiv.org/abs/2605.24468