About this paper
MixUA distills lessons from independent user-agent trajectories and assigns them to appropriate scopes to balance cross-user and cross-agent learning with privacy, evaluated by CrossLearnBench.
Self-evolving agents improve their own skills, memory, and harness code from experience without retraining the base LLM, and group-evolving agents go further by sharing these lessons across agents. Yet most such systems overlook that sharing across users and heterogeneous agents requires deciding who can benefit from each lesson and what information must remain private. We present MixUA, a memory system that distills independent user-agent trajectories into lessons and assigns each lesson to a user-agent pair, user, agent, or global scope according to whom it benefits and what it may disclose. For evaluation, we introduce CrossLearnBench, a mixed-user-agent benchmark that pairs established…
self-evolving agentsgroup-evolving agentsbase LLMmemory systemuser-agent trajectorieslessonsuser-agent pairglobal scopeCrossLearnBenchmixed-user-agent benchmark
- Upvotes
- 3
- Authors
- 5
- Published
- Nov 7, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
Who Remembers What? Multi-Granularity Memory Extraction for Multi-User, Multi-Agent Interaction was first seen on Hugging Face · Daily papers on Nov 14, 2026. Since then it has appeared in 26 checks on 3 different days. Its best position was #15 of 30, reached on Nov 16, 03:28 UTC. It is #16 right now, climbing from #21 to #16 over the last 6 checks.