Introduces OPT* tasks and two training regimes (solver-guided online policy optimization with rank-based reward shaping and search-based offline RL) plus a theoretical link between search success and information extraction per budget unit, showing empirical gains in optimization-like reasoning.
hub
Reasoning gym: Reasoning environments for reinforcement learning with verifiable rewards.arXiv preprint arXiv:2505.24760
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 2
dataset 2
citation-polarity summary
verdicts
UNVERDICTED 16representative citing papers
Fast-Slow Training uses context optimization as fast weights alongside parameter updates as slow weights to achieve up to 3x better sample efficiency, higher performance, and less catastrophic forgetting than standard RL in continual LLM learning.
TRON supplies 520 rule-verifiable online visual reasoning environments across five ability buckets that generate unlimited training instances for RL post-training, yielding consistent gains on ten external multimodal benchmarks for three vision-language models.
XLGoBench applies algorithmic tasks to expose persistent cross-lingual performance gaps in state-of-the-art LLMs.
K2V extends RLVR to knowledge-intensive domains by synthesizing verifiable data and verifying reasoning processes, yielding improved domain reasoning with preserved general capabilities.
AIPO adds active multi-agent consultation (Verify, Knowledge, Reasoning agents) plus custom importance sampling to RLVR training so LLMs expand their reasoning boundary and then operate without the agents.
RL training compute for logical reasoning follows a power law with horizon depth whose exponent rises with logical expressiveness, yielding better downstream transfer when models train on richer logics.
QuickScope uses modified COUP Bayesian optimization to find truly difficult questions in dynamic LLM benchmarks more sample-efficiently than baselines while cutting false positives.
Systematic false positives in verifiers can cause RLVR training to reach suboptimal plateaus or collapse, with outcomes driven by error patterns rather than overall error rate.
SCALER creates adaptive synthetic environments for RL-based LLM reasoning training that outperforms fixed-dataset baselines with more stable long-term progress.
SPHINX generates synthetic visual puzzles for benchmarking LVLMs, where GPT-5 scores 51.1% and RLVR training improves both in-domain and external visual reasoning performance.
RREDCoT approximates segment-level reward redistribution for CoT traces by querying the model itself, offering a lower-cost alternative to Monte Carlo credit assignment in reasoning-model RL.
The paper identifies four missing interfaces (data autolabelling, embodiment retargeting, physics-grounded world models, and video-based reward inference) as the central bottleneck beyond VLA scaling for robot intelligence.
Gym-V supplies 179 visual environments showing that observation scaffolding like captions and rules matters more for training success than the choice of RL algorithm.
TokUR estimates token-level uncertainty via low-rank weight perturbations in LLMs, aggregates signals to correlate with correctness, and uses them to improve reasoning performance on math tasks.
Mellum 2 is a 12B MoE model with 2.5B active parameters, trained on 10.6T tokens with MoE, GQA, SWA, and MTP, then post-trained into Instruct and Thinking variants, claimed competitive with 4B-14B models at 2.5B compute.
citing papers explorer
-
Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces
Introduces OPT* tasks and two training regimes (solver-guided online policy optimization with rank-based reward shaping and search-based offline RL) plus a theoretical link between search success and information extraction per budget unit, showing empirical gains in optimization-like reasoning.
-
TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL
TRON supplies 520 rule-verifiable online visual reasoning environments across five ability buckets that generate unlimited training instances for RL post-training, yielding consistent gains on ten external multimodal benchmarks for three vision-language models.
-
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
RL training compute for logical reasoning follows a power law with horizon depth whose exponent rises with logical expressiveness, yielding better downstream transfer when models train on richer logics.
-
SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning
SCALER creates adaptive synthetic environments for RL-based LLM reasoning training that outperforms fixed-dataset baselines with more stable long-term progress.