UniOPSD: Unifying Outcome and Hindsight Feedback for Agentic Reinforcement LearningResearchSep 29, 2026
DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning ModelsResearchSep 29, 2026
AG-CoT: Verified Algorithmic Traces for LLM Program Synthesis on Clifford CircuitsResearchSep 29, 2026
From Soft Targets to Reward Signals: How Assignment and Reward Objectives InteractResearchSep 29, 2026
Fewer Assumptions by Design: A Reusable Skill for LLM-Assisted Verus VerificationResearchSep 29, 2026
When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement LearningResearchSep 29, 2026
Simulating Respondents, Not Single Questions: Coherent Survey Generation with Large Language ModelsResearchSep 29, 2026
LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear PayoffsResearchSep 29, 2026