paper-with-me

Papers

InfMem: Learning System-2 Memory Control for Long-Context Agent

2026-02-02 · Xinyu Wang, Mingze Li, Peng Lu, Xiao-Wen Chang, Lifeng Shang, Jinping Li, Fei Mi, Prasanna Parthasarathi, Yufei Cui arxiv

Reasoning over ultra-long documents requires synthesizing sparse evidence scattered across distant segments under strict memory constraints. While streaming agents enable scalable processing, their passive memory update strategy often fails to preserve low-salience bridging evidence required for multi-hop reasoning. We propose InfMem, a control-centric agent that instantiates System-2-style control via a PreThink-Retrieve-Write protocol. InfMem actively monitors evidence sufficiency, performs targeted in-document retrieval, and applies evidence-aware joint compression to update a bounded memory. To ensure reliable control, we introduce a practical SFT-to-RL training recipe that aligns retrieval, writing, and stopping decisions with end-task correctness. On ultra-long QA benchmarks from 32k to 1M tokens, InfMem consistently outperforms MemAgent across backbones. Specifically, InfMem improves average absolute accuracy by +10.17, +11.84, and +8.23 points on Qwen3-1.7B, Qwen3-4B, and Qwen2.5-7B, respectively, while reducing inference time by $3.9\times$ on average (up to $5.1\times$) via adaptive early stopping.

📄 PDF Abstract BibTeX arXiv:2602.02704

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Imitation Learning for End to End Vehicle Longitudinal Control with Forward Camera

2018-12-14 · Laurent George, Thibault Buhet, Emilie Wirbel, Gaetan Le-Gall 외

In this paper we present a complete study of an end-to-end imitation learning system for speed control of a real car, based on a neural network with a Long Short Term Memory (LSTM). To achieve robustness and generalizati…

Data AugmentationImitation Learning

Multi-Layered Memory Architectures for LLM Agents: An Experimental Evaluation of Long-Term Context Retention

2026-03-31 · Sunil Tiwari, Payal Fofadiya arxiv

Long-horizon dialogue systems suffer from semanticdrift and unstable memory retention across extended sessions. This paper presents a Multi-Layer Memory Framework that decomposes dialogue history into working, episodic, …

Computational Efficiency

LoL-PIM: Long-Context LLM Decoding with Scalable DRAM-PIM System

2024-12-28 · Hyucksung Kwon, Kyungmo Koo, Janghyeon Kim, Woongkyu Lee 외

The expansion of large language models (LLMs) with hundreds of billions of parameters presents significant challenges to computational resources, particularly data movement and memory bandwidth. Long-context LLMs, which …

GPUManagement

QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management

2025-12-15 · Weizhou Shen, Ziyi Yang, Chenliang Li, Zhiyuan Lu 외 arxiv

We introduce QwenLong-L1.5, a model that achieves superior long-context reasoning capabilities through systematic post-training innovations. The key technical breakthroughs of QwenLong-L1.5 are as follows: (1) Long-Conte…

Reinforcement Learning

Can Agent Memory Systems Track Evolving State?

2026-08-20 · Xinyi Fan, Miri Liu, Ruozhen Yang, Siru Ouyang 외 arxiv

As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps. While existing memory benchmarks focus largely on recall-shaped tasks, we argue an effective memory…