MaxIM frames incremental memory summarization as an RL reward-shaping problem
A variational mutual-information critic supplies dense rewards so bounded summaries stay predictive of future task targets.
Stories per day · 30 days
Relatedcontext-compression1dialogue1language-agents1masked-reconstruction1memory1mutual-information1reinforcement-learning1
3 stories, newest first · one card per story
Stories tagged #summarization
SUMONE summarizer compresses agent histories by 78% on DeepSearchQA
SUMONE summarizes trajectories via masked reconstruction and GRPO reward for task-agnostic plug-and-play compression.
Unifying Conformal Language Tasks with In-Context Ensembles
Researchers propose Conformal Relevance, which builds conformal score functions via in-context example curation and ensembling to improve conciseness across seven NLP tasks.