Alternatives and similar repositories for CMPhysBench

Users that are interested in CMPhysBench are comparing it to the libraries listed below

• spiral-rl / spiral
  SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
  ☆161Updated last month
• rhyang2021 / ARIA
  Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".
  ☆24Updated 2 months ago
• sail-sg / AnytimeReasoner
  Optimizing Anytime Reasoning via Budget Relative Policy Optimization
  ☆47Updated 3 months ago
• xufangzhi / Genius
  [ACL 2025] A Generalizable and Purely Unsupervised Self-Training Framework
  ☆71Updated 5 months ago
• TIGER-AI-Lab / Hierarchical-Reasoner
  Emergent Hierarchical Reasoning in LLMs/VLMs through Reinforcement Learning
  ☆46Updated 2 weeks ago
• XinrunXu / DeepPHY
  DeepPHY: Benchmarking Agentic VLMs on Physical Reasoning
  ☆157Updated 2 months ago
• ASTRAL-Group / AlphaOne
  [EMNLP 2025 Main] AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
  ☆85Updated 4 months ago
• sail-sg / feedback-conditional-policy
  Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"
  ☆51Updated last month
• Xuekai-Zhu / FlowRL
  ☆105Updated this week
• beichenzbc / BoostStep
  official code for "BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning"
  ☆36Updated 9 months ago
• hkust-nlp / model-task-align-rl
  The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".
  ☆15Updated 2 months ago
• RUCAIBox / R1-Searcher-plus
  R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning
  ☆64Updated 5 months ago
• yuleiqin / RAIF
  A Recipe for Building LLM Reasoners to Solve Complex Instructions
  ☆27Updated last month
• zhijie-group / SIFT
  SIFT: Grounding LLM Reasoning in Contexts via Stickers
  ☆58Updated 8 months ago
• JieyuZ2 / TaskMeAnything
  [NeurIPS 2024] A task generation and model evaluation system for multimodal language models.
  ☆73Updated 11 months ago
• euclid-multimodal / Euclid
  ☆17Updated 10 months ago
• Gen-Verse / CURE
  [NeurIPS 2025 Spotlight] ReasonFlux-Coder: Open-Source LLM Coders with Co-Evolving Reinforcement Learning
  ☆131Updated last month
• wmn-231314 / diffusion-data-constraint
  Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…
  ☆103Updated last week
• SalesforceAIResearch / LATTE
  ☆68Updated last month
• mandyyyyii / east
  ☆20Updated 3 months ago
• zhiyuanhubj / Meta-Ability-Alignment
  Official code of paper "Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models"
  ☆81Updated 5 months ago
• Gabesarch / ICAL
  ☆50Updated 5 months ago
• test-time-interaction / TTI
  ☆63Updated 4 months ago
• opendatalab / REST
  ☆32Updated 3 months ago
• LLM360 / Reasoning360
  A repo for open research on building large reasoning models
  ☆110Updated last week
• yunfeixie233 / ViGaL
  ☆61Updated 2 weeks ago
• NVlabs / NFT
  Implementation of Negative-aware Finetuning (NFT) algorithm for "Bridging Supervised Learning and Reinforcement Learning in Math Reasonin…
  ☆46Updated 2 months ago
• NuoJohnChen / JudgeLRM
  JudgeLRM: Large Reasoning Models as a Judge
  ☆40Updated last month
• JingMog / THOR
  Official Implementation of our paper "THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning".
  ☆27Updated last month
• Gen-Verse / dLLM-RL
  TraceRL & TraDo-8B: Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
  ☆296Updated 2 weeks ago