Papers arxiv:2605.09063 Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs Published on May 9 Submitted by GUIJIN SON on May 12 2 Paper of the day EleutherAI Authors: , Seungone Kim , Catherine Arnett , Hyunwoo Ko , , , , , , , , Sang Park , , , Seungy… …
… AI-generated summary Recent progress in reasoning models has substantially advanced long-horizon mathematical and scientific problem solving , with several systems now reaching gold-medal-level performance on International Mathematical Olympiad IMO and International Physics Olympiad IPhO problems. …
… The following papers were recommended by the Semantic Scholar API Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning 2026 Think Anywhere in Code Generation 2026 HintMR: Eliciting Stronger Mathematical Reasoning in Small Language Models 2026 Efficient… …
… AI-generated summary Large language models LLMs have achieved remarkable progress in mathematical reasoning , but this ability is not equally accessible across languages. Especially low-resource languages exhibit much lower reasoning performance. …
Papers arxiv:2605.09806 LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models Published on May 10 Submitted by Songtao Wei on May 14 University of Texas at Dallas Authors: Songtao Wei , , , , , , , , , Abstract LEAD is a method that dynamically adapts reasoning efficiency … …
… If you feel interested, can be reached out by chenyang.zhao@sglang.ai Would also be nice to include the performance of Qwen2.5-Math-Instruct and Qwen2.5-7B-Instruct to quantify the improvement using reasoning trace SFT distillation. How exactly is the Qwen/Qwen2.5-Math-RM-72B model used? …
… Notably, ResRL surpasses NSR on mathematical reasoning by 9.4\% in Avg@16 and 7.0\% in Pass@128. Code is available at https://github.com/1229095296/ResRL.git. …
… The following papers were recommended by the Semantic Scholar API The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning 2026 Hyperagents 2026 AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery 2026 Deep Research of De… …
… These tokens depart from one correct path yet remain verified, making them both self-driven and valuable exploration. 🌟 And the results? 📈 RLRT consistently outperforms GRPO, self-distillation, and exploration baselines across base, instruction-tuned, and thinking-tuned Qwen3 models on 6 math bench… …
… The following papers were recommended by the Semantic Scholar API CLORE: Content-Level Optimization for Reasoning Efficiency 2026 How You Begin is How You Reason: Driving Exploration in RLVR via Prefix-Tuned Priors 2026 SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adap… …