The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published 16 days ago • 161
openai/whisper-large-v3-turbo Automatic Speech Recognition • 0.8B • Updated Oct 4, 2024 • 7.92M • • 3.16k
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models Paper • 2605.30219 • Published May 28 • 26
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 431
The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation Paper • 2605.21856 • Published May 21 • 8
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration Paper • 2605.20025 • Published May 19 • 191
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues Paper • 2605.12493 • Published May 12 • 5