Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models Paper • 2505.10554 • Published May 15 • 121
Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? Paper • 2508.19827 • Published 12 days ago • 30 • 2
Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation Paper • 2210.12902 • Published Oct 24, 2022
Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? Paper • 2508.19827 • Published 12 days ago • 30
Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? Paper • 2508.19827 • Published 12 days ago • 30
IntrEx Collection IntrEx is the first large-scale dataset annotated for interestingness and expected interestingness in teacher-student interactions • 2 items • Updated 16 days ago
IntrEx Collection IntrEx is the first large-scale dataset annotated for interestingness and expected interestingness in teacher-student interactions • 2 items • Updated 16 days ago
Spectrum Projection Score: Aligning Retrieved Summaries with Reader Models in Retrieval-Augmented Generation Paper • 2508.05909 • Published Aug 8 • 20
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems Paper • 2508.07407 • Published 29 days ago • 90