arXiv AI
On Language Drift during RLVR Post-Training
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
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
Jun 2
RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning
arXiv:2606. 01281v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs).
Hugging Face Trending Papers
3d ago
Aligning Thoughts with Answers: Probability Rewards to Tame Thinking Drift
This paper studies \textbf{thinking--answer consistency} in vision-language models. We focus on Visual Intention Grounding, where a model infers a target object based on a human intention query and pr...
arXiv Computation and Language
Aug 28
Boosting LLM Exploration via Weak-Model Guidance in RLVR
The paper introduces a method to enhance large language model (LLM) exploration in Reinforcement Learning with Verifiable Rewards (RLVR) by guiding the target model with partial reasoning trajectories from smaller, weaker language models. This weak-model guidance disrupts over‑confidence, preserves generative diversity, and mitigates entropy collapse without extra fine‑tuning or complex reward designs. Experiments on mathematical benchmarks show consistent improvements over vanilla RLVR, especially as the number of allowed attempts ($k$) increases, indicating broader reasoning coverage.
arXiv Machine Learning
Aug 27
Demystifying Reinforcement Learning Post-Training of Language Models
The paper "Demystifying Reinforcement Learning Post-Training of Language Models" investigates how reinforcement learning (RL) post‑training enhances large language models (LLMs) for tasks such as reasoning, math, and coding. By isolating RL components in a controlled setting, the authors analyze how the base model’s prior distribution, reward granularity, prompt diversity, and model scale influence outcomes, using policy entropy to compare pre‑training, supervised fine‑tuning (SFT), and RL stages. The study clarifies the role of spurious rewards, the importance of the base model’s probability mass on desired behaviors, and how these factors interact to determine post‑training success, offering a practical primer for NLP researchers. "whyItMatters":"The work provides a clearer understanding of RL post‑training mechanics, helping researchers and practitioners effectively apply RL to improve LLM capabilities."
arXiv AI
2d ago
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
The paper introduces POISE, a reinforcement learning algorithm that uses a model’s internal states as a value estimator to reduce variance in reinforcement learning with verifiable rewards (RLVR). By employing a lightweight probe that reads internal signals during the forward pass, POISE predicts baselines online and uses a cross‑rollout construction to keep gradients unbiased. Experiments on Qwen3‑4B and OLMo3‑7B‑Instruct‑DPO across six domains show POISE outperforms existing RLVR baselines, offering more stable training and a value model that generalizes across tasks and scales with the policy.