RLVR

Timeline

1. Oct 8, 2026 · Research paper · 1 source
   Residual Advantage: Student-Relative Teacher Guidance for RL with Verifiable Rewards
   We propose Residual Advantage (\RA{}), which treats the teacher--student probability residual as a bounded one-step reward, subtracts the corresponding state value under the student policy to form a standard advantage, and centers the result within each response before adding it to the verifier advantage.
2. Oct 8, 2026 · Research paper · 1 source
   RL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty
   To this end, we propose RL-ARC, a calibration-aware training framework that jointly leverages reasoning confidence and answer confidence.
3. Oct 8, 2026 · Research paper · 1 source
   When Interfaces Speak: Data-Aware Generative UI Harness for Active Interaction
   We propose GenUI-Harness, a multi-agent harness pairing a Tool Agent for information retrieval and task execution with a GUI Coder Agent that identifies ambiguities and generates front-end code for structured interfaces.
4. Oct 8, 2026 · Research paper · 1 source
   Measuring and Mitigating Solution Mode Collapse in RLVR
   A language model (LM) can usually answer the same question in more than one way, but reinforcement learning with verifiable rewards (RLVR) is indifferent to which correct answer a model produces.
5. Oct 7, 2026 · Research paper · 1 source
   SPLIT-RL: Staged Perception-Language Reasoning Training with Claim-Level Advantages
   Vision-Language (VL) reasoning requires a model to both extract relevant and accurate information from an image (visual reasoning, VR), and to infer the answer from it (language reasoning, LR).
6. Oct 7, 2026 · Research paper · 1 source
   VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning
   Reinforcement learning with verifiable rewards (RLVR) has become a standard recipe for post-training vision-language models (VLMs),
7. Oct 7, 2026 · Research paper · 1 source
   Decoupling Exploration from Optimization in RLVR
   Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints.
8. Oct 7, 2026 · Research paper · 1 source
   Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents
   In this paper, we systematically investigate how intermediate supervision can improve reinforcement learning for search agents.
9. Oct 7, 2026 · Research paper · 1 source
   RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving Reward Adaptation
   We introduce RewardWeaver, a self-evolving reward adaptation framework for language agents in long-horizon interaction.
10. Oct 6, 2026 · Research paper · 2 sources
    Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
    Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after interaction.
11. Sep 28, 2026 · Research paper · 1 source
    Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors
    Reinforcement learning (RL) has become a key paradigm for enhancing the reasoning of large language models, yet the high dimensionality of parameter updates makes its training dynamics hard to analyze.
12. Sep 28, 2026 · Research paper · 1 source
    ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning
    To address this, we propose ReSPO (Reshaped Sequence Policy Optimization), which replaces clipping with a smooth, two-branch sequence-level kernel derived from an α-divergence variational objective and an exponential variance-control tilt.

Often appears with