How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review Paper • 2608.08975 • Published 13 days ago • 48
Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning Paper • 2608.02831 • Published 20 days ago • 13
TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning Paper • 2607.08940 • Published Jul 9 • 2
TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning Paper • 2510.03519 • Published Oct 3, 2025 • 1
Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction Paper • 2606.28186 • Published Jun 26 • 9
WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems Paper • 2603.14392 • Published May 19
Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models Paper • 2606.16700 • Published Jun 15 • 15
Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models Paper • 2606.16700 • Published Jun 15 • 15
Guava: An Effective and Universal Harness for Embodied Manipulation Paper • 2606.18363 • Published Jun 16 • 28
AI, Take the Wheel: What Drives Delegation and Trust in Human-Computer Cooperative Question Answering? Paper • 2605.28255 • Published May 27 • 1
Sandboxed Coding Agents are Competitive Omni-modal Task Solvers Paper • 2606.00579 • Published May 30 • 2
Skip a Layer or Loop It? Learning Program-of-Layers in LLMs Paper • 2606.06574 • Published Jun 4 • 25
Multiple LLM Agents Debate for Equitable Cultural Alignment Paper • 2505.24671 • Published Sep 1, 2025
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks Paper • 2604.20987 • Published Apr 22 • 22