paper-with-me

홈 › Papers

Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents

2026-05-20 · Chongrui Ye, Yuxiang Liu, Yu Wang, Haofei Yu, Yining Zhao, Ge Liu, Julian McAuley, Jiaxuan You arxiv

Language agents increasingly operate over streams of related tasks, yet existing memory systems struggle to convert accumulated experience into reusable knowledge. Retrieval-augmented and structured memory methods record per-session observations effectively, but often couple acquisition and consolidation into a single online process, leaving the agent without a global view across sessions to discover recurring patterns, abstract shared procedures, or prune redundant entries. Inspired by complementary learning systems theory, we propose Auto-Dreamer, a learned offline consolidator for language-agent memory. Auto-Dreamer decouples fast per-session memory acquisition from slow cross-session consolidation. Given a selected working region of a typed memory bank, the consolidator treats the region as read-only evidence, performs bounded tool-use to inspect entries and provenance-linked source trajectories, and synthesizes a fresh compact replacement set that abstracts across sessions and supersedes the original region. We train Auto-Dreamer via GRPO, using end-to-end agent performance as the reward signal to learn how to consolidate memories acquired through fast online experience. Trained on ScienceWorld trajectories alone, Auto-Dreamer outperforms fixed, RL-trained, and prompted memory baselines on ScienceWorld by 7 points while using an active memory bank 12$\times$ smaller than the strongest baseline, and continues to lead on held-out ALFWorld and WebArena without retraining -- using 6$\times$ less memory than the strongest baseline on ALFWorld.

📄 PDF Abstract BibTeX arXiv:2605.20616

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Lightweight LLM Agent Memory with Small Language Models

2026-04-09 · Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Zhenzhen Huang 외 arxiv

Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions. However, retrieval-based external memo…

SCM: Sleep-Consolidated Memory with Algorithmic Forgetting for Large Language Models

2026-04-22 · Saish Sachin Shinde arxiv

We present SCM (Sleep-Consolidated Memory), a research preview of a memory architecture for large language models that draws on neuroscientific principles to address a fundamental limitation in current systems: the absen…

MyGO: Memory Yielding Generative Offline-consolidation for Lifelong Learning Systems

2025-08-29 · Shihao Ji, Zihui Song arxiv

Continual or Lifelong Learning aims to develop models capable of acquiring new knowledge from a sequence of tasks without catastrophically forgetting what has been learned before. Existing approaches often rely on storin…

Knowledge Distillation

Why the Brain Consolidates: Predictive Forgetting for Optimal Generalisation

2026-03-05 · Zafeirios Fountas, Adnan Oomerjee, Haitham Bou-Ammar, Jun Wang 외 arxiv

Standard accounts of memory consolidation emphasise the stabilisation of stored representations, but struggle to explain representational drift, semanticisation, or the necessity of offline replay. Here we propose that h…

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…