Research
EvoBelief: Falsifiable World Models for Self-Improving LLM Agents (opens in a new tab)
arXiv cs.AI ·
Your next cue,
from NOCUE.
Research
One-Step Text Generation by Seq-Drifting (opens in a new tab)
arXiv cs.AI ·
Research
Collaborative Theory of Mind: Learning to Self-Revise by Anticipating User Responses (opens in a new tab)
arXiv cs.AI ·
Research
SmartSalesBench: A Resistance-Aware Multi-Turn Benchmark for Evaluating LLM Sales Agents (opens in a new tab)
arXiv cs.AI ·
Research
Benchmarking Embedding Geometries and Clustering Algorithms for Unsupervised Patent Claim Classification (opens in a new tab)
arXiv cs.AI ·
Research
Neural networks are more modular than single neurons suggest (opens in a new tab)
arXiv cs.AI ·
Research
EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents (opens in a new tab)
arXiv cs.AI ·
Research
Hindsight Structured Advice Distillation: Steering Executor Agents with Advisors Trained on Their Failures and Task Characteristics (opens in a new tab)
arXiv cs.AI ·
Research
Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training (opens in a new tab)
arXiv cs.AI ·