arXiv AI
Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 9
Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short
arXiv:2606. 09380v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a leading paradigm for improving the reasoning ability of large language models through outcome-based supervision.
arXiv AI
Jul 23
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
arXiv:2601. 06487v3 Announce Type: replace-cross Abstract: Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast solution spaces (e.
arXiv AI
5d ago
How to Train a Critic Stably and Efficiently
The paper introduces Best‑Practice Critic Optimization (BPCO), a stable and efficient recipe for training a critic in reinforcement learning for large language models. BPCO combines DPPO, bounded value predictions, Monte Carlo targets, unnormalized policy advantages, and length‑adaptive advantage estimation, allowing the critic to be conditioned on hidden reward information. Experiments on mathematical reasoning tasks with models from 1.5B to 30B parameters show that BPCO consistently outperforms a strong critic‑based baseline and matches or exceeds group‑based methods while sampling only one response per prompt.
arXiv AI
4d ago
Best Practice Critic Optimization
arXiv:2608.23566v2 Announce Type: replace-cross Abstract: Group-based reinforcement learning methods such as GRPO for large language models avoid training a critic by sampling multiple responses for...
arXiv Machine Learning
Jul 3
Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling
arXiv:2607. 01830v1 Announce Type: new Abstract: Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks.
Hugging Face Trending Papers
Jul 2
Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling
Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompose such judgments into explicit evaluation criteria, but existing annotation-free rubric generators typically rely on a single generic evaluator.