arXiv AI
CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 28
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
arXiv:2509. 03059v2 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforcement Learning with Verifiable Reward (RLVR), particularly in domains like mathematics and programming, where ground-truth correctness can be automatically evaluated.
arXiv Machine Learning
20h ago
LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data
arXiv:2610.30132v1 Announce Type: cross Abstract: Reinforcement learning (RL) is an effective way to strengthen the long-context reasoning of large language models (LLMs), but it needs training data...
arXiv Machine Learning
Jun 5
SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions
arXiv:2604. 08477v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has substantially improved reasoning in formal domains such as mathematics and code, but extending these gains beyond STEM remains challenging.
arXiv Machine Learning
Sep 10
Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning
arXiv:2604.02007v3 Announce Type: replace Abstract: Building general-purpose reasoning models using reinforcement learning with verifiable rewards (RLVR) across diverse domains has been widely adopte...
arXiv AI
Oct 1
ArgGYM: A Procedural, Engine-Verified Benchmark for Structured Defeasible Reasoning
arXiv:2609.38409v1 Announce Type: new Abstract: Recent progress in large language model reasoning has been driven by benchmarks and reinforcement learning environments with automatically verifiable r...
arXiv Computation and Language
Aug 27
InternBootcamp: Boosting LLM Reasoning with Verifiable Task Scaling
InternBootcamp is an open‑source framework that offers over 1,000 domain‑diverse task environments for large language model (LLM) reasoning research. It introduces Bootcamp‑Eval, an automatically generated benchmark for comprehensive performance assessment. Experiments show that training on InternBootcamp significantly improves reasoning performance, with a 32B model achieving state‑of‑the‑art results on Bootcamp‑Eval and other established benchmarks, demonstrating that scaling the number of training tasks yields consistent gains.