MEM1 uses end-to-end RL to learn constant-memory agents that update a shared state for memory and reasoning, delivering 3.5x better performance and 3.7x lower memory use than larger baselines on long-horizon QA and shopping tasks.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
Causely supplies a live causal model anchored to an ontology that cuts AI agent diagnosis time by 63 percent, token use by 60 percent, and raises root-cause accuracy from 75 percent to 100 percent in a controlled 24-service benchmark.
SDSR places human metadata at file primacy and combines it with prompt routing rules to reach 100% primary category accuracy on a 119-category benchmark, far above the 65% no-guidance baseline.
TableMaster improves LM table understanding by verbalizing tables with enriched semantics and using adaptive textual-symbolic reasoning, reaching 78.13% accuracy on WikiTQ with GPT-4o-mini.
Large language models using zero-shot and few-shot prompting achieve reasonably strong performance on named entity recognition for historical texts on the HIPE-2022 dataset.
citing papers explorer
-
MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents
MEM1 uses end-to-end RL to learn constant-memory agents that update a shared state for memory and reasoning, delivering 3.5x better performance and 3.7x lower memory use than larger baselines on long-horizon QA and shopping tasks.
-
Causely: A Causal Intelligence Layer for Enterprise AI A Benchmark Study on SRE and Reliability Workflows
Causely supplies a live causal model anchored to an ontology that cuts AI agent diagnosis time by 63 percent, token use by 60 percent, and raises root-cause accuracy from 75 percent to 100 percent in a controlled 24-service benchmark.
-
Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation
SDSR places human metadata at file primacy and combines it with prompt routing rules to reach 100% primary category accuracy on a 119-category benchmark, far above the 65% no-guidance baseline.
-
TableMaster: A Recipe to Advance Table Understanding with Language Models
TableMaster improves LM table understanding by verbalizing tables with enriched semantics and using adaptive textual-symbolic reasoning, reaching 78.13% accuracy on WikiTQ with GPT-4o-mini.
-
Named Entity Recognition of Historical Texts via Large Language Model
Large language models using zero-shot and few-shot prompting achieve reasonably strong performance on named entity recognition for historical texts on the HIPE-2022 dataset.