method · first seen 7 Oct 2026
self-play training
Also: self-play
Training a model by having it generate outputs and learn from discrepancies against reference outputs.
Mentions per week
PapersCodeDiscussion
Rank 160 on 16 Nov 2026 · 12 mentions in 28 days · 12 independent groups · papers → code · first seen 6 weeks ago · acceleration -0.42
Earliest sources
- From Hitter to Player: Separating Motor Execution and Strategy in Competitive Humanoid Table TennisPapers · 7 Oct 2026 · Fanrong Dong, Ziyi Sun, Ziqi Han, Junhan Sun, Lei Ye, Zetong Jing, Hao Zhao, Sha…
- SP-DocReader: Difference-Aware Self-Play for Precise Document OCRPapers · 8 Oct 2026 · Wenjie Liao, Xiaohui Song, Liangjie Zhao, Haonan Lu
- Training LLMs for Multi-Agent Collaboration with Verifiable Information RewardsPapers · 13 Oct 2026 · Keru Chen, Sen Lin, Yingbin Liang, Nathaniel D. Bastian, Shaofeng Zou
- Explorer-Zero: Improving Self-Play for Long-Horizon Tasks with Decomposable Verifiable RewardsPapers · 14 Oct 2026 · Tianyu Liu, Davide Belli, Bence Major, Arash Behboodi, Tribhuvanesh Orekondy
- Selection Is Not Learning: Choosing Model FuturesPapers · 15 Oct 2026 · Haoyi Yang, Kshitij Mishra, Nils Lukas, Salem Lahlou
- R$^2$Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization LoopPapers · 15 Oct 2026 · Mingda Zhang, Yun Huang, Qiang Huang, Yanjin Li, Rui Qian, Qichao Zhao, Tiesunlo…
Latest sources
- When Will You Hand It Over? A Hidden Start Delay Makes Self-Play Handover Robust to Unfamiliar PartnersPapers · 13 Nov 2026 · Mohammad Khoshnazar, Mike Degany, Deyuan Qu, Qing Yang, Matyas Szanto
- Toward LLM Self-Play Under Data Scarcity: Effectiveness, Generalizability, and TrustworthinessPapers · 6 Nov 2026 · Zhiyin Yu, Yuchen Mou, Bingzhe Wu, Zhonghai Wu, Shiyang Feng, Xiao Luo
- Test-Time Self-Play: Scaling without a VerifierPapers · 5 Nov 2026 · Akira Yoshiyama, Akmal Ashirmatov, Jonas Hübotter, Ido Hakimi, Andreas Krause
- When Can Self-Play Fix a False Belief? Answer Keys, Pass Bands and Replacement Rules in an Execution-Grounded LoopPapers · 4 Nov 2026 · Nirdesh Chauhan, Dushyant Rajput, Siddharth Kosaraju
- Perturb, Repair, Verify: Self-Play Vision-Language Verifiers for Compositional UnderstandingPapers · 3 Nov 2026 · Zijun Huang, Yingjun Du, Cees G. M. Snoek
- kevinz917/superhuman-polytopia-botCode · 29 Oct 2026 · kevinz917 · 36 stars
- EpiAgent: Epistemic Self-Play for LLM AgentsPapers · 29 Oct 2026 · Xuanfa Jin, Xinyu Cui, Zhijian Ma, Xue Yan, Jian Zhao, Haifeng Zhang, Jun Wang
- CoSTA: Co-Evolving Self-Play Timeline Agents for Complex Temporal Knowledge Graph Question AnsweringPapers · 28 Oct 2026 · Haikun Liu, Zhichao Yan, Shaoru Guo, Jiawei Gu, Victor Gutierrez Basulto, Jiapu…
- Evolve on Graph: Self-Evolving Knowledge Graph Reasoning without Question AnnotationsPapers · 26 Oct 2026 · Zongyuan Sun, Shuai Zhao, Ke Shu, Ziyue Zhu, Shangyang Wu, Yuanlin Lin, Tao Wang…
- Tempo-Zero: Recursive Self-Play in Executable Worlds for Video ReasoningPapers · 23 Oct 2026 · Jingmin Zhu, Yanyan Zou, Xiuyu Li, James Bailey, Dinh Phung, Tao Yu, Yunyun Hou,…
- TerraTransfer++: Demonstration-Free End-to-End PlannerPapers · 21 Oct 2026 · Zikang Xiong, Weixin Li, Zhouchonghao Wu, Akshay Rangesh, Saarth Bonde, Grantlan…
- The Predictive--Optimization Gap in GuanDan Self-PlayPapers · 21 Oct 2026 · Qicheng Zou, Biao Yuan, Siyu Song, Wentao Liu, Xiaokun Wang