Librarian Bot. I found the following papers similar to this paper. \n
The following papers were recommended by the Semantic Scholar API
\n- \n
- StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models (2025) \n
- InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling (2025) \n
- VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains (2025) \n
- The Challenge of Teaching Reasoning to LLMs Without RL or Distillation (2025) \n
- MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization (2025) \n
- Agentar-DeepFinance-300K: A Large-Scale Financial Dataset via Systematic Chain-of-Thought Synthesis Optimization (2025) \n
- Omni-Think: Scaling Cross-Domain Generalization in LLMs via Multi-Task RL with Hybrid Rewards (2025) \n
Please give a thumbs up to this comment if you found it helpful!
\nIf you want recommendations for any Paper on Hugging Face checkout this Space
\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
Papers
arxiv:2509.03059
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
Published on Sep 3, 2025
Abstract
The Loong Project introduces a framework for generating and verifying synthetic data to improve reasoning capabilities in Large Language Models through Reinforcement Learning with Verifiable Reward.
AI-generated summary
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. However, extending this success to other reasoning-intensive domains remains challenging due to the scarcity of high-quality, verifiable datasets and the high cost of human supervision. In this work, we introduce the Loong Project: an open-source framework for scalable synthetic data generation and verification across a diverse range of reasoning-intensive domains. The framework consists of two key components: (1) LoongBench, a curated seed dataset containing 8,729 human-vetted examples across 12 domains (e.g., Advanced Mathematics, Chemistry, Logic), each paired with executable code and rich metadata; and (2) LoongEnv, a modular synthetic data generation environment that supports multiple prompting strategies to produce new question-answer-code triples. Together, these components form an agent-environment loop that enables reinforcement learning, where an LLM-based agent is rewarded for generating Chain-of-Thought (CoT) solutions that align with code-executed answers. Empirically, we benchmark LoongBench on a broad suite of both open-source and proprietary LLMs to evaluate domain coverage and reveal performance bottlenecks. In addition, we conduct a comprehensive analysis of synthetic data generated by LoongEnv, examining correctness, difficulty, and diversity. Code and documentation are available at https://github.com/camel-ai/loong.
Community
We introduce Project Loong: focusing on scaling up synthetic data generation with verifiers for a broad range of domains. We believe that synthetic data generation is essential—not only for addressing gaps in data-scarce domains, but also for enhancing reasoning capabilities in areas like math and programming by expanding dataset availability.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models (2025)
- InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling (2025)
- VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains (2025)
- The Challenge of Teaching Reasoning to LLMs Without RL or Distillation (2025)
- MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization (2025)
- Agentar-DeepFinance-300K: A Large-Scale Financial Dataset via Systematic Chain-of-Thought Synthesis Optimization (2025)
- Omni-Think: Scaling Cross-Domain Generalization in LLMs via Multi-Task RL with Hybrid Rewards (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2509.03059 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2509.03059 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2509.03059 in a Space README.md to link it from this page.