Trendoday

Who Remembers What? Multi-Granularity Memory Extraction for Multi-User, Multi-Agent Interaction

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. Ye

  • Upvotes3
#16Rank now 1
#15Peak rank
3Days on list
186Score · 7d
Nov 14, 2026First seen
Rank · 7 days

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.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 Nov 14Nov 14Nov 15Nov 15Nov 16 Nov 14, 03:28 UTC · #27Nov 14, 05:28 UTC · #23Nov 14, 07:28 UTC · #23Nov 14, 09:28 UTC · #23Nov 14, 11:28 UTC · #23Nov 14, 13:28 UTC · #23Nov 14, 15:28 UTC · #21Nov 14, 17:28 UTC · #21Nov 14, 19:28 UTC · #21Nov 14, 21:28 UTC · #21Nov 14, 23:28 UTC · #21Nov 15, 01:28 UTC · #21Nov 15, 03:28 UTC · #21Nov 15, 05:28 UTC · #21Nov 15, 07:28 UTC · #21Nov 15, 09:28 UTC · #21Nov 15, 11:28 UTC · #21Nov 15, 13:28 UTC · #21Nov 15, 15:28 UTC · #21Nov 15, 17:28 UTC · #21Nov 15, 19:28 UTC · #21Nov 15, 21:28 UTC · #21Nov 15, 23:28 UTC · #18Nov 16, 01:28 UTC · #18Nov 16, 03:28 UTC · #15Nov 16, 05:28 UTC · #16

Last 14 days

Best rank per day (UTC).

Nov 3today

Metric history

▲ as reported by Hugging Face.

05914 Nov 14Nov 14Nov 15Nov 15Nov 16 Nov 14, 03:28 UTC · 3Nov 14, 05:28 UTC · 5Nov 14, 07:28 UTC · 5Nov 14, 09:28 UTC · 5Nov 14, 11:28 UTC · 5Nov 14, 13:28 UTC · 5Nov 14, 15:28 UTC · 6Nov 14, 17:28 UTC · 7Nov 14, 19:28 UTC · 7Nov 14, 21:28 UTC · 7Nov 14, 23:28 UTC · 7Nov 15, 01:28 UTC · 7Nov 15, 03:28 UTC · 7Nov 15, 05:28 UTC · 7Nov 15, 07:28 UTC · 8Nov 15, 09:28 UTC · 8Nov 15, 11:28 UTC · 8Nov 15, 13:28 UTC · 8Nov 15, 15:28 UTC · 8Nov 15, 17:28 UTC · 8Nov 15, 19:28 UTC · 8Nov 15, 21:28 UTC · 8Nov 15, 23:28 UTC · 13Nov 16, 01:28 UTC · 13Nov 16, 03:28 UTC · 14Nov 16, 05:28 UTC · 14

Questions

Is Who Remembers What? Multi-Granularity Memory Extraction for Multi-User, Multi-Agent Interaction trending on HF Daily Papers right now?

Yes. As of Nov 16, 05:28 UTC it is #16, climbing from #21 to #16 over the last 6 checks.

What is the highest rank Who Remembers What? Multi-Granularity Memory Extraction for Multi-User, Multi-Agent Interaction reached?

#15 on Hugging Face · Daily papers, on Nov 16, 03:28 UTC. Trendoday checks this list every 120 minutes.

How long has Who Remembers What? Multi-Granularity Memory Extraction for Multi-User, Multi-Agent Interaction been trending?

It was first seen on Nov 14, 2026 and has been on the list on 3 days (26 checks) since.