Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Wenzhe Fan, Ning Yan, Masood Mortazavi• 2025

Related benchmarks

TaskDatasetResultRank
Mathematical ReasoningAIME 2024
Accuracy26.7
525
Mathematical ReasoningAIME 2025
Pass@1 Accuracy30
192
Mathematical ReasoningAIME 2023
Accuracy (%)13.3
36
Mathematical ReasoningAIME 2022
Accuracy (Exact Match)13.3
12
Multi-domain reasoningAFlow-Stream (test)
GSM8K Accuracy94
11
Code GenerationHard Code Stream MBPP+, CC, HumanEval
MBPP+ Accuracy88.5
7
Mathematical ReasoningMATH hard Level 4 5
Accuracy (Exact Match)55.3
7
Mathematical ReasoningHard Math Stream Overall
Accuracy (micro-average)44.5
7
Mathematical ReasoningHard Math Stream (test)
Accuracy (Hard Math Stream)88.2
4
Showing 9 of 9 rows

Other info

Follow for update