papers_rl.yaml

- short_name: RTMC
  title: 'RTMC: Step-Level Credit Assignment via Rollout Trees'
  authors: Tao Wang, Suhang Zheng, Xiaoxiao Xu
  year: '2026'
  venue: arXiv preprint arXiv:2604.11037
  month: 2026-04
  links:
    arxiv: https://arxiv.org/abs/2604.11037
- short_name: SWE-Fuse
  title: 'SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning
    and Entropy-aware RLVR Training'
  authors: Xin-Cheng Wen, Binbin Chen, Haoxuan Lan, Hang Yu, Peng Di, Cuiyun Gao
  year: '2026'
  venue: arXiv preprint arXiv:2603.07927
  month: 2026-03
  links:
    arxiv: https://arxiv.org/abs/2603.07927
- short_name: SWE-Master
  title: 'SWE-Master: Unleashing the Potential of Software Engineering Agents via
    Post-Training'
  authors: Huatong Song, Lisheng Huang, Shuang Sun, Jinhao Jiang, Ran Le, Daixuan
    Cheng, Guoxin Chen, Yiwen Hu, Zongchao Chen, Wayne Xin Zhao, Yang Song, Tao Zhang,
    Ji-Rong Wen
  year: '2026'
  venue: arXiv preprint arXiv:2602.03411
  month: 2026-02
  links:
    arxiv: https://arxiv.org/abs/2602.03411
    github: https://github.com/RUCAIBox/SWE-Master
- short_name: SWE-Protégé
  title: 'SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks
    Small Language Models as Software Engineering Agents'
  authors: Patrick Tser Jern Kon, Archana Pradeep, Ang Chen, Alexander P. Ellis, Warren
    Hunt, Zijian Wang, John Yang, Samuel Thompson
  year: '2026'
  venue: arXiv preprint arXiv:2602.22124
  month: 2026-02
  links:
    arxiv: https://arxiv.org/abs/2602.22124
- short_name: SWE-MiniSandbox
  title: 'SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software
    Engineering Agents'
  authors: Danlong Yuan, Wei Wu, Zhengren Wang, Xueliang Zhao, Huishuai Zhang, Dongyan
    Zhao
  year: '2026'
  venue: arXiv preprint arXiv:2602.11210
  month: 2026-02
  links:
    arxiv: https://arxiv.org/abs/2602.11210v1
    github: http://github.com/lblankl/SWE-MiniSandbox
- short_name: MiMo-V2-Flash
  title: MiMo-V2-Flash Technical Report
  authors: Xiaomi-LLM-Core-Team, Bangjun Xiao, Bingquan Xia, Bo Yang, Bofei Gao, Bowen
    Shen, Chen Zhang et al.
  year: '2026'
  venue: arXiv preprint arXiv:2601.02780
  month: 2026-01
  links:
    arxiv: https://arxiv.org/abs/2601.02780
- short_name: SWE-Manager
  title: 'SWE-Manager: Selecting and Synthesizing Golden Proposals Before Coding'
  authors: Boyin Tan, Haoning Deng, Junyuan Zhang, Junjielong Xu, Pinjia He, Youcheng
    Sun
  year: '2026'
  venue: arXiv preprint arXiv:2601.22956
  month: 2026-01
  links:
    arxiv: https://arxiv.org/abs/2601.22956
    github: https://github.com/shuaijiumei/SWE-Manager
- short_name: Self-play SWE-RL
  title: Toward Training Superintelligent Software Agents through Self-Play SWE-RL
  authors: Yuxiang Wei, Zhiqing Sun, Emily McMilin, Jonas Gehring, David Zhang, Gabriel
    Synnaeve, Daniel Fried et al.
  year: '2025'
  venue: arXiv preprint arXiv:2512.18552
  month: 2025-12
  links:
    arxiv: https://arxiv.org/abs/2512.18552
- short_name: SWE-Playground
  title: Training Versatile Coding Agents in Synthetic Environments
  authors: Yiqi Zhu, Apurva Gandhi, Graham Neubig
  year: '2025'
  venue: arXiv preprint arXiv:2512.12216
  month: 2025-12
  links:
    arxiv: https://arxiv.org/abs/2512.12216
- short_name: SWE-RM
  title: 'SWE-RM: Execution-free Feedback For Software Engineering Agents'
  authors: KaShun Shum, Binyuan Hui, Jiawei Chen, Lei Zhang, X. W., Jiaxi Yang, Yuzhen
    Huang et al.
  year: '2025'
  venue: arXiv preprint arXiv:2512.21919
  month: 2025-12
  links:
    arxiv: https://arxiv.org/abs/2512.21919
- short_name: One Tool Is Enough
  title: 'One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents'
  authors: Zhaoxi Zhang, Yitong Duan, Yanzhi Zhang, Yiming Xu, Weikang Li, Jiahui
    Liang, Deguo Xia et al.
  year: '2025'
  venue: arXiv preprint arXiv:2512.20957
  month: 2025-12
  links:
    arxiv: https://arxiv.org/abs/2512.20957
- short_name: Let It Flow
  title: 'Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model
    within an Open Agentic Learning Ecosystem'
  authors: Weixun Wang, XiaoXiao Xu, Wanhe An, Fangwen Dai, Wei Gao, Yancheng He,
    Ju Huang et al.
  year: '2025'
  venue: arXiv preprint arXiv:2512.24873
  month: 2025-12
  links:
    arxiv: https://arxiv.org/abs/2512.24873
- short_name: Deepseek V3.2
  title: 'DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models'
  authors: DeepSeek-AI, Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang,
    Bingzheng Xu et al.
  year: '2025'
  venue: arXiv preprint arXiv:2512.02556
  month: 2025-12
  links:
    arxiv: https://arxiv.org/abs/2512.02556
- short_name: TSP
  title: 'Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level
    Code Repair'
  authors: Xiong, Bojian, Lei, Yikun, Liu, Xikai, Zhang, Shaowei, Zhu, Pengyun, Liu,
    Yan, Leng, Yongqi et al.
  year: '2025'
  venue: 'Proceedings of the 2025 Conference on Empirical Methods in Natural Language
    Processing: Industry Track 2025'
  month: 2025-11
  links:
    doi: https://aclanthology.org/2025.emnlp-industry.109/
- short_name: CWM
  title: 'CWM: An Open-Weights LLM for Research on Code Generation with World Models'
  authors: FAIR CodeGen team, Jade Copet, Quentin Carbonneaux, Gal Cohen, Jonas Gehring,
    Jacob Kahn, Jannik Kossen et al.
  year: '2025'
  venue: arXiv preprint arXiv:2510.02387
  month: 2025-10
  links:
    arxiv: https://arxiv.org/abs/2510.02387
- short_name: FoldGRPO
  title: Scaling Long-Horizon LLM Agent via Context-Folding
  authors: Weiwei Sun, Miao Lu, Zhan Ling, Kang Liu, Xuesong Yao, Yiming Yang, Jiecao
    Chen
  year: '2025'
  venue: arXiv preprint arXiv:2510.11967
  month: 2025-10
  links:
    arxiv: https://arxiv.org/abs/2510.11967
- short_name: GRPO-based Method
  title: A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning
  authors: Ruiyi Wang, Prithviraj Ammanabrolu
  year: '2025'
  venue: First Workshop on Multi-Turn Interactions in Large Language Models 2025
  month: 2025-10
  links:
    arxiv: https://arxiv.org/abs/2510.01132
    website: https://neurips.cc/virtual/2025/loc/san-diego/127960
    openreview: https://openreview.net/forum?id=yPWJG9wgll
- short_name: Supervised RL
  title: 'Supervised Reinforcement Learning: From Expert Trajectories to Step-wise
    Reasoning'
  authors: Yihe Deng, I-Hung Hsu, Jun Yan, Zifeng Wang, Rujun Han, Gufeng Zhang, Yanfei
    Chen et al.
  year: '2025'
  venue: arXiv preprint arXiv:2510.25992
  month: 2025-10
  links:
    arxiv: https://arxiv.org/abs/2510.25992
- short_name: KAT-Coder
  title: KAT-Coder Technical Report
  authors: Zizheng Zhan, Ken Deng, Jinghui Wang, Xiaojiang Zhang, Huaixi Tang, Minglei
    Zhang, Zhiyi Lai et al.
  year: '2025'
  venue: arXiv preprint arXiv:2510.18779
  month: 2025-10
  links:
    arxiv: https://arxiv.org/abs/2510.18779
- short_name: CoreThink
  title: 'CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks
    with LLMs'
  authors: Jay Vaghasiya, Omkar Ghugarkar, Vishvesh Bhat, Vipul Dholaria, Julian McAuley
  year: '2025'
  venue: arXiv preprint arXiv:2509.00971
  month: 2025-09
  links:
    arxiv: https://arxiv.org/abs/2509.00971
- short_name: EntroPO
  title: Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization
  authors: Jiahao Yu, Zelei Cheng, Xian Wu, Xinyu Xing
  year: '2025'
  venue: arXiv preprint arXiv:2509.12434
  month: 2025-09
  links:
    arxiv: https://arxiv.org/abs/2509.12434
- short_name: Kimi-Dev
  title: 'Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents'
  authors: Zonghan Yang, Shengjie Wang, Kelin Fu, Wenyang He, Weimin Xiong, Yibo Liu,
    Yibo Miao et al.
  year: '2025'
  venue: arXiv preprint arXiv:2509.23045
  month: 2025-09
  links:
    arxiv: https://arxiv.org/abs/2509.23045
- short_name: LongCat-Flash-Think
  title: 'Introducing LongCat-Flash-Thinking: A Technical Report'
  authors: Meituan-LongCat-Team, Anchun Gui, Bei Li, Bingyang Tao, Bole Zhou, Borun
    Chen, Chao Zhang et al.
  year: '2025'
  venue: arXiv preprint arXiv:2509.18883
  month: 2025-09
  links:
    arxiv: https://arxiv.org/abs/2509.18883
- short_name: Tool-integrated RL
  title: Tool-integrated Reinforcement Learning for Repo Deep Search
  authors: Zexiong Ma, Chao Peng, Qunhong Zeng, Pengfei Gao, Yanzhen Zou, Bing Xie
  year: '2025'
  venue: arXiv preprint arXiv:2508.03012
  month: 2025-08
  links:
    arxiv: https://arxiv.org/abs/2508.03012
- short_name: SWE-Swiss
  title: 'SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue
    Resolution'
  authors: He, Zhenyu, Yang, Qingping, Sheng, Wei, Zhong, Xiaojian, Zhang, Kechi,
    An, Chenxin, Shi, Wenlei et al.
  year: '2025'
  venue: '-'
  month: 2025-08
  links:
    website: https://www.notion.so/SWE-Swiss-A-Multi-Task-Fine-Tuning-and-RL-Recipe-for-High-Performance-Issue-Resolution-21e174dedd4880ea829ed4c861c44f88
- short_name: SeamlessFlow
  title: 'SeamlessFlow: A Trainer Agent Isolation RL Framework Achieving Bubble-Free
    Pipelines via Tag Scheduling'
  authors: Jinghui Wang, Shaojie Wang, Yinghan Cui, Xuxing Chen, Chao Wang, Xiaojiang
    Zhang, Minglei Zhang et al.
  year: '2025'
  venue: arXiv preprint arXiv:2508.11553
  month: 2025-08
  links:
    arxiv: https://arxiv.org/abs/2508.11553
- short_name: DAPO
  title: Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement
    Learning
  authors: Alexander Golubev, Maria Trofimova, Sergei Polezhaev, Ibragim Badertdinov,
    Maksim Nekrashevich, Anton Shevtsov, Simon Karasik et al.
  year: '2025'
  venue: arXiv preprint arXiv:2508.03501
  month: 2025-08
  links:
    arxiv: https://arxiv.org/abs/2508.03501
- short_name: GLM-4.6
  title: gpt-oss-120b & gpt-oss-20b model card
  authors: Agarwal, Sandhini, Ahmad, Lama, Ai, Jason, Altman, Sam, Applebaum, Andy,
    Arbus, Edwin, Arora, Rahul K et al.
  year: '2025'
  venue: arXiv preprint arXiv:2508.10925
  month: 2025-08
  links:
    arxiv: https://arxiv.org/abs/2508.10925
- short_name: DeepSWE
  title: 'DeepSWE: Training a State-of-the-Art Coding Agent from Scratch by Scaling
    RL'
  authors: Michael Luo, Naman Jain, Jaskirat Singh, Sijun Tan, Ameen Patel, Qingyang
    Wu, Alpay Ariyak et al.
  year: '2025'
  venue: '-'
  month: 2025-07
  links:
    website: https://pretty-radio-b75.notion.site/DeepSWE-Training-a-Fully-Open-sourced-State-of-the-Art-Coding-Agent-by-Scaling-RL-22281902c1468193aabbe9a8c59bbe33
- short_name: Kimi-K2-Instruct
  title: 'Kimi K2: Open Agentic Intelligence'
  authors: Kimi Team, Yifan Bai, Yiping Bao, Guanduo Chen, Jiahao Chen, Ningxin Chen,
    Ruijue Chen et al.
  year: '2025'
  venue: arXiv preprint arXiv:2507.20534
  month: 2025-07
  links:
    arxiv: https://arxiv.org/abs/2507.20534
- short_name: Agent-RLVR
  title: 'Agent-RLVR: Training Software Engineering Agents via Guidance and Environment
    Rewards'
  authors: Jeff Da, Clinton Wang, Xiang Deng, Yuntao Ma, Nikhil Barhate, Sean Hendryx
  year: '2025'
  venue: arXiv preprint arXiv:2506.11425
  month: 2025-06
  links:
    arxiv: https://arxiv.org/abs/2506.11425
- short_name: SWE-Dev2
  title: 'SWE-Dev: Building Software Engineering Agents with Training and Inference
    Scaling'
  authors: Haoran Wang, Zhenyu Hou, Yao Wei, Jie Tang, Yuxiao Dong
  year: '2025'
  venue: arXiv preprint arXiv:2506.07636
  month: 2025-06
  links:
    arxiv: https://arxiv.org/abs/2506.07636
- short_name: Minimax M2
  title: 'MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention'
  authors: Chen, Aili, Li, Aonian, Gong, Bangwei, Jiang, Binyang, Fei, Bo, Yang, Bo,
    Shan, Boji et al.
  year: '2025'
  venue: arXiv preprint arXiv:2506.13585
  month: 2025-06
  links:
    arxiv: https://arxiv.org/abs/2506.13585
- short_name: SWE-Dev1
  title: 'SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development'
  authors: Yaxin Du, Yuzhu Cai, Yifan Zhou, Cheng Wang, Yu Qian, Xianghe Pang, Qian
    Liu et al.
  year: '2025'
  venue: arXiv preprint arXiv:2505.16975
  month: 2025-05
  links:
    arxiv: https://arxiv.org/abs/2505.16975
- short_name: Satori-SWE
  title: 'Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software
    Engineering'
  authors: Guangtao Zeng, Maohao Shen, Delin Chen, Zhenting Qi, Subhro Das, Dan Gutfreund,
    David Cox et al.
  year: '2025'
  venue: arXiv preprint arXiv:2505.23604
  month: 2025-05
  links:
    arxiv: https://arxiv.org/abs/2505.23604
- short_name: Qwen3-Coder
  title: Qwen3 Technical Report
  authors: An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng,
    Bowen Yu et al.
  year: '2025'
  venue: arXiv preprint arXiv:2505.09388
  month: 2025-05
  links:
    arxiv: https://arxiv.org/abs/2505.09388
- short_name: Seed1.5-Thinking
  title: 'Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning'
  authors: ByteDance Seed, :, Jiaze Chen, Tiantian Fan, Xin Liu, Lingjun Liu, Zhiqi
    Lin et al.
  year: '2025'
  venue: arXiv preprint arXiv:2504.13914
  month: 2025-04
  links:
    arxiv: https://arxiv.org/abs/2504.13914
- short_name: SEAlign
  title: 'SEAlign: Alignment Training for Software Engineering Agent'
  authors: Kechi Zhang, Huangzhao Zhang, Ge Li, Jinliang You, Jia Li, Yunfei Zhao,
    Zhi Jin
  year: '2025'
  venue: ICSE 2026
  month: 2025-03
  links:
    arxiv: https://arxiv.org/abs/2503.18455
    doi: https://conf.researchr.org/details/icse-2026/icse-2026-research-track/46/SEAlign-Alignment-Training-for-Software-Engineering-Agent
- short_name: SWE-RL
  title: 'SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software
    Evolution'
  authors: Yuxiang Wei, Olivier Duchenne, Jade Copet, Quentin Carbonneaux, LINGMING
    ZHANG, Daniel Fried, Gabriel Synnaeve et al.
  year: '2025'
  venue: The Thirty-ninth Annual Conference on Neural Information Processing Systems
    2025
  month: 2025-02
  links:
    arxiv: https://arxiv.org/abs/2502.18449v2
    openreview: https://openreview.net/forum?id=ULblO61XZ0
- short_name: SoRFT
  title: 'SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning'
  authors: Zexiong Ma, Chao Peng, Pengfei Gao, Xiangxin Meng, Yanzhen Zou, Bing Xie
  year: '2025'
  venue: "Proceedings of the 63rd Annual Meeting of the Association for Computational\n\
    \                  Linguistics (Volume 1: Long Papers), ACL 2025, Vienna, Austria,\n\
    \                  July 27 - August 1, 2025 2025"
  month: 2025-02
  links:
    arxiv: https://arxiv.org/abs/2502.20127v1
- short_name: OSCA
  title: Scaling LLM Inference Efficiently with Optimized Sample Compute Allocation
  authors: Zhang, Kexun, Zhou, Shang, Wang, Danqing, Wang, William Yang, Li, Lei
  year: '2024'
  venue: 'Proceedings of the 2025 Conference of the Nations of the Americas Chapter
    of the Association for Computational Linguistics: Human Language Technologies
    (Volume 1: Long Papers) 2025'
  month: 2024-10
  links:
    arxiv: https://arxiv.org/abs/2410.22480
    doi: https://aclanthology.org/2025.naacl-long.404/