DOLORES, an agent using a formal language for meta-reasoning to construct adaptive scaffolds on the fly, outperforms prior scaffolding methods by 24.8% on average across four hard benchmarks and multiple model sizes.
Working Memory Identifies Reasoning Limits in Language Models , booktitle =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Noisy memory encoding of determiners explains negative polarity illusions, with new acceptability experiments showing stronger illusions for similar determiner pairs.
MADRAG combines multi-agent debate with retrieval-augmented generation to produce training-free analytic essay scores that outperform prompt baselines and approach supervised systems.
Explicit memory modeled on the hippocampus is the cornerstone needed to advance LLMs to AGI because their implicit statistical learning cannot produce higher cognitive functions.
citing papers explorer
-
Deep Reasoning in General Purpose Agents via Structured Meta-Cognition
DOLORES, an agent using a formal language for meta-reasoning to construct adaptive scaffolds on the fly, outperforms prior scaffolding methods by 24.8% on average across four hard benchmarks and multiple model sizes.
-
Noisy memory encoding explains negative polarity illusions
Noisy memory encoding of determiners explains negative polarity illusions, with new acceptability experiments showing stronger illusions for similar determiner pairs.
-
MADRAG: Multi-Agent Debate with Retrieval-Augmented Generation for Training-Free Analytic Essay Scoring
MADRAG combines multi-agent debate with retrieval-augmented generation to produce training-free analytic essay scores that outperform prompt baselines and approach supervised systems.
-
Position: Hippocampal Explicit Memory Is the Cornerstone for AGI
Explicit memory modeled on the hippocampus is the cornerstone needed to advance LLMs to AGI because their implicit statistical learning cannot produce higher cognitive functions.