arXiv AI
Learning to Solve Hard Problems in RL for LLMs by Never Giving Up
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
sGPO: Trading Inference FLOPs for Training Efficiency in RLVR
arXiv:2606. 08854v1 Announce Type: cross Abstract: Standard Reinforcement Learning with Verifiable Rewards (RLVR) training allocates a fixed rollout budget to every query, without regard for what each query's difficulty means for the current policy.
arXiv Machine Learning
Jun 9
The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning
arXiv:2606. 07950v1 Announce Type: new Abstract: RL with verifiable rewards can substantially improve LLM reasoning, yet standard GRPO-style training often treats easy, hard, and learnable questions alike through uniform sampling and weighting, leading to inefficient compute allocation.
arXiv Machine Learning
Jul 3
DecompRL: Solving Harder Problems by Learning Modular Code Generation
arXiv:2607. 02390v1 Announce Type: new Abstract: How can Large Language Models (LLMs) solve problems they currently cannot?
arXiv Machine Learning
Aug 26
Mitigating Exploration Bias in RL for Multi-Instruction Following
arXiv:2608.23830v1 Announce Type: cross Abstract: RL has emerged as a powerful paradigm for enhancing the instruction following capabilities of LLMs. While existing training recipes achieve substanti...
arXiv Machine Learning
Jul 10
HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning
arXiv:2601. 22448v2 Announce Type: replace Abstract: RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts are sampled and when.
arXiv AI
4d ago
Nice Fold or Hero Call: Learning Budget-Efficient Thinking under Policy-Dependent Solvability
The paper introduces Budget‑Efficient Thinking (BET), a two‑stage framework that treats adaptive reasoning as a computational investment, aligning solve‑or‑fold decisions with expected return rather than perceived difficulty. BET learns three distinct behaviors: concise short solves for easy queries, early abstention (nice fold) when further reasoning is unlikely to pay off, and allocating sufficient compute (hero call) for hard‑but‑solvable questions. Experiments on seven benchmarks with three base models show BET cuts reasoning tokens by 54% while boosting accuracy by up to 3.2%, and it transfers effectively to scientific QA and logical reasoning tasks.