LPM encodes personal history as N latent slots projected by cross-attention into input-conditioned soft prompts for frozen LLMs, reporting up to 8.8% higher accuracy than LoRA and 64x lower KV-cache on PersonaMem v1 plus matching LoRA accuracy with 120x fewer parameters on LoCoMo.
Memory3: Language modeling with explicit memory.Journal of Machine Learning, 3(3):300–346, January 2024
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
citing papers explorer
-
Latent Personal Memory: Represent personal memory as dynamic soft prompts
LPM encodes personal history as N latent slots projected by cross-attention into input-conditioned soft prompts for frozen LLMs, reporting up to 8.8% higher accuracy than LoRA and 64x lower KV-cache on PersonaMem v1 plus matching LoRA accuracy with 120x fewer parameters on LoCoMo.
-
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.