ACADEMIC & FRONTIER RESEARCH PIPELINE

AI Research Papers & Preprints

Curated from arXiv, Semantic Scholar, Hugging Face Papers, OpenReview, Nature Machine Intelligence, Stanford SAIL, MIT CSAIL, and BAIR.

arXiv:2611.17338·arXiv Artificial Intelligence (cs.AI)·3 hours ago
Score: 78/100 · Citations: 0

When Should LLM Agents Forget? Memory Filtering Under Query-Critical Resolver Errors

Authors: Samarth Vinayaka
AI Synthesis: The available reporting indicates from arXiv Artificial Intelligence (cs.AI) that arXiv:2611.17338v1 Announce Type: new Abstract: LLM memory systems often delete facts classified as stale. We show that this hard-filtering step can reduce downstream accuracy when resolver errors delete query-critical facts. Across three
Read Paper Abstract & Impact Analysis

arXiv:2611.17338v1 Announce Type: new Abstract: LLM memory systems often delete facts classified as stale. We show that this hard-filtering step can reduce downstream accuracy when resolver errors delete query-critical facts. Across three models, a controlled sensitivity...

Why it matters: This development in LLMs provides actionable signal for engineering, research, and policy teams monitoring arXiv Artificial Intelligence (cs.AI).

LLMsAI AgentsResearch

University & Research Labs (18)

Semantic Scholar AI
semanticscholar.org · US
96/100
Science Magazine AI
science.org · US
99/100
96/100
Hugging Face Daily Papers
huggingface.co · US
95/100
99/100
Stanford AI Lab (SAIL)
stanford.edu · US
98/100
Stanford HAI
hai.stanford.edu · US
98/100
98/100
97/100
Vector Institute
vectorinstitute.ai · CA
97/100
ETH Zurich AI Center
ai.ethz.ch · CH
98/100
98/100
Berkeley AI Research (BAIR)
bair.berkeley.edu · US
98/100
Kyutai Open Science Lab
kyutai.org · FR
91/100
MIT CSAIL & AI News
news.mit.edu · US
98/100