paper-with-me

Papers

EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory

2025-11-01 · Wenzhe Fan, Ning Yan, Masood Mortazavi arxiv

Planning has been a cornerstone of artificial intelligence for solving complex problems, and recent progress in LLM-based multi-agent frameworks have begun to extend this capability. However, the role of human-like memory within these frameworks remains largely unexplored. Understanding how agents coordinate through memory is critical for natural language planning, where iterative reasoning, constraint tracking, and error correction drive the success. Inspired by working memory model in cognitive psychology, we present EvoMem, a multi-agent framework built on a dual-evolving memory mechanism. The framework consists of three agents (Constraint Extractor, Verifier, and Actor) and two memory modules: Constraint Memory (CMem), which evolves across queries by storing task-specific rules and constraints while remains fixed within a query, and Query-feedback Memory (QMem), which evolves within a query by accumulating feedback across iterations for solution refinement. Both memory modules are reset at the end of each query session. Evaluations on trip planning, meeting planning, and calendar scheduling show consistent performance improvements, highlighting the effectiveness of EvoMem. This success underscores the importance of memory in enhancing multi-agent planning.

📄 PDF Abstract BibTeX arXiv:2511.01912

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective

2026-05-18 · Yuyao Wang, Zhongjian Zhang, Mo Chi, Kaichi Yu 외 arxiv

Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it enables them to store, update, and retrieve information over…

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

2026-06-11 · Jundong Xu, Qingchuan Li, Jiaying Wu, Yihuai Lan 외 arxiv

Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deployment is inherently dynamic, requiring agent…

EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation

2026-06-02 · Zuhao Ge, Xiaosong Jia, Chao Wu, Yuchen Zhou 외 arxiv

Building memory is essential for long-horizon planning in zero-shot embodied navigation. Detector-centric scene graphs often compress observations into sparse nodes, discarding fine-grained visual evidence and accumulati…

Zero-shot Generalization3D Reconstruction

Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution

2026-06-27 · Shuang Cui, Fan Ji, Guanglong Sun, Yufei Guo 외 arxiv

Real-world image restoration (IR) remains challenging due to complex and coupled degradations. While recent agentic IR frameworks leverage Large Language Models for flexible tool planning, they face two critical limitati…

Image Restoration

S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research

2026-02-02 · S1-NexusAgent Team arxiv

Modern scientific research relies on large-scale data, complex workflows, and specialized tools, which existing LLMs and tool-based agents struggle to handle due to limitations in long-horizon planning, robust goal maint…

Continual Learning