arXiv Machine Learning
Learned Reporting Preferences in RLVR Can Conflict with the Current Request
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Aug 18
Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR
arXiv:2605. 02909v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a powerful approach for improving the reasoning capabilities of large language models (LLMs).
arXiv AI
2d ago
Visual sensitivity is not claim retractability: persistence-aware credit assignment for multimodal reinforcement learning
arXiv:2609.36572v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been extended to Large Vision-Language Models (LVLMs), and perception-aware methods further e...
arXiv AI
Aug 11
Improving Generalization Robustness of Multimodal RLVR
arXiv:2608. 08802v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasing a question or changing the prompt template can degrade them, which challenges reliable deployment in high-stakes scenarios like medical VQA.
arXiv AI
Jul 29
CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization
arXiv:2607. 25659v1 Announce Type: new Abstract: Rubric-based reinforcement learning enriches language model training by evaluating model outputs against explicit criteria.
arXiv Machine Learning
Jun 5
Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents
arXiv:2606. 05263v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves reasoning and tool use, yet long-horizon language agents still learn unsupported evidence chains, belief drift, and shortcut actions that satisfy terminal checks.
arXiv AI
Sep 1
Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning
arXiv:2605.11467v2 Announce Type: replace-cross Abstract: Reasoning models post-hoc rationalize answers they have already committed to internally, producing chains of *reasoning theater*: deliberativ...