MemShot renders local dialogue spans as structured visual memory units to improve long-term dialogue modeling in LLMs, achieving competitive benchmark performance with 70x faster memory construction.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
MemForest speeds up agent memory writes about 6x by parallelizing extraction and using a hierarchical temporal index, while matching or beating stateful baselines on LongMemEval-S.
FLP uses multi-persona foresight simulation to detect infections via response diversity and applies local purification to reduce maximum cumulative infection rates in multi-agent systems from over 95% to below 5.47%.
EvoRec deploys four collaborating LLM agents that co-evolve recommendation models and their optimization methods, reporting up to 5.54% offline gains and 1.85% revenue lift in an online A/B test.
LLM agents enable a shift in recommender systems from opaque hidden profiles to governable, inspectable, and portable user representations.
citing papers explorer
-
Memory Shot for Long-Term Dialogue
MemShot renders local dialogue spans as structured visual memory units to improve long-term dialogue modeling in LLMs, achieving competitive benchmark performance with 70x faster memory construction.
-
MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
MemForest speeds up agent memory writes about 6x by parallelizing extraction and using a hierarchical temporal index, while matching or beating stateful baselines on LongMemEval-S.
-
Catching the Infection Before It Spreads: Foresight-Guided Defense in Multi-Agent Systems
FLP uses multi-persona foresight simulation to detect infections via response diversity and applies local purification to reduce maximum cumulative infection rates in multi-agent systems from over 95% to below 5.47%.
-
EvoRec: Self Evolving Agentic Recommender Systems
EvoRec deploys four collaborating LLM agents that co-evolve recommendation models and their optimization methods, reporting up to 5.54% offline gains and 1.85% revenue lift in an online A/B test.
-
From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents
LLM agents enable a shift in recommender systems from opaque hidden profiles to governable, inspectable, and portable user representations.