paper-with-me

홈 › Papers

PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction

2026-07-03 · Zhuoqun Li, Boxi Cao, Jiawei Chen, Hanshu Zhou, Ruoxi Xu, Guiping Jiang, Ruotong Pan, Tingting Gao, Han Li, Xiangyu Wu, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun hf

Long-horizon behavior prediction aims to infer a user's next action based on a lengthy historical sequence, playing a crucial role in artificial intelligence field. The rise of large language models (LLMs) offers a promising direction for sequential behavior prediction, yet LLMs struggle with latent behavioral pattern induction and model-intrinsic cognitive biases when tackling long-horizon behavior prediction. Prior memory management methods follow a context-compression paradigm that attempts to address this task by alleviating the historical sequence burden, yet fail to resolve the core challenges. In this paper, we advocate a paradigm shift that reframes the lengthy historical sequence from a burden into a valuable resource to be exploited, and accordingly propose PraMem, which conducts beforehand practice over the lengthy historical sequence to build an experiential memory, thereby serving as the assisted input for accurate long-horizon behavior prediction. Extensive experiments across diverse tasks demonstrate that PraMem achieves superior performance than prior methods, and more in-depth analyses provide valuable insights into the mechanism and evolution of the experiential memory. Code: https://github.com/icip-cas/PraMem.

📄 PDF Abstract BibTeX arXiv:2607.02881

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses

2026-08-25 · Zhaochen Yu, Yingcheng Wu, Zhenfei Yin, Kaiyuan Chen 외 hf

Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We introduce Recuris, a recursive Experiential-Working Memory architectur…

Smarter Together: Creating Agentic Communities of Practice through Shared Experiential Learning

2025-11-11 · Valentin Tablan, Scott Taylor, Gabriel Hurtado, Kristoffer Bernhem 외 arxiv

The transition from human-centric to agent-centric software development practices is disrupting existing knowledge sharing environments for software developers. Traditional peer-to-peer repositories and developer communi…

Continual LearningCode Generation

Evaluating Long-Term Memory for Long-Context Question Answering

2025-10-27 · Alessandra Terranova, Björn Ross, Alexandra Birch arxiv

In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains u…

Question Answering

ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction

2026-08-21 · Linhao Zhong, Zongze Du, Linyu Wu, Yu Bo 외 arxiv

Open-web future event prediction requires agents to distill reliable signals from noisy, redundant, and incomplete evidence. Existing retrieval/memory mechanisms directly feed retrieved information to agents or rely on s…

MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution

2026-04-29 · Chunzheng Zhu, Jiaqi Zeng, Junyu Jiang, Jianxin Lin 외 arxiv

High-precision medical diagnosis relies not only on static imaging features but also on the implicit diagnostic memory experts instantly invoke during image interpretation. We pinpoint a fundamental cognitive misalignmen…

Reinforcement LearningMedical Diagnosis