| 1 | AdaRSI: On-Demand Recursive Self-Improvement for Embodied Agents | Peidong Wang, Ying Chang, Zhiming Ma +8 | cs.CL | 2026-10-14 |
| 2 | SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm | Qianru Meng, Xi Zhang, Konstantinos Papakostas +9 | cs.AI | 2026-10-14 |
| 3 | MMLA-RSI: Recursive Self-Improvement through RTT and RTMA | Junyi Zou, Avrova Donz | cs.CL | 2026-10-14 |
| #4 | Exact Cut Complexity of Equal-Length Proportional Cake Cutting | Yasushi Kawase, Bodhayan Roy, Mohammad Azharuddin Sanpui | cs.MA | 2026-10-14 |
| #5 | Synthetic reaction data from transformation rules for graph-to-sequence pretraining in biodegradation pathway prediction | Irsyaad Rijwan, Liam Brydon, Aidan Jared +1 | cs.LG | 2026-10-14 |
| #6 | VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness | Zihao Lin, Haoyu Dong, Haobo Xu +10 | cs.CV | 2026-10-14 |
| #7 | Recursive Formation and First-Class Reuse of Compositional Capabilities | Hang Lin | cs.PL | 2026-10-14 |
| #8 | Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards | Wenbo Hu, Shraman Pramanick, Krishna Kumar Singh +3 | cs.CL | 2026-10-13 |
| #9 | The Last Remote Sensing Model Built by Humans? Casting Any Earth Observation Task as Recursive Self-Improvement | Sijie Zhao, Zeqi Zhou, Heli Qi +6 | cs.CV | 2026-10-13 |
| #10 | Who Improves the Robot? Toward Physical Recursive Self-Improvement | Hai Zhou, Fan Yang, Zeyi Chen +27 | cs.AI | 2026-10-13 |
| #11 | Depth Memory | David González-Martínez, Philipp Nazari, T. Konstantin Rusch +1 | cs.LG | 2026-10-13 |
| #12 | Emergent Loop Geometry in Gauge-Equivariant Graph Neural Networks | Ali Rayat, Gia-Wei Chern | cond-mat.stat-mech | 2026-10-13 |
| #13 | RSIgen: Reciprocal Self-Improvement for Agentic Visual Generation | Yidi Liu, Haozhe Wang, Jie Xiao +3 | cs.CV | 2026-10-13 |
| #14 | Tiny Recursive Message Passing | Tommaso Salvatori, Matteo Forasassi, Alexis Toumi +1 | cs.LG | 2026-10-13 |
| #15 | Input-Conditioned Search for Efficient Test-Time Scaling of Recursive Reasoners | Haochen Shi, Tianwen Fu, Qianggang Ding +7 | cs.AI | 2026-10-13 |
| #16 | LongForcing: Scaling Temporal Manifold Matching for Long-Horizon World Rollout | Ziyu Zhu, Zhaoxu Sun, Fan Jiang +5 | cs.CV | 2026-10-13 |
| #17 | APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation | Sirui Zhang, Fangyun Wei, Dong Chen +5 | cs.CV | 2026-10-13 |
| #18 | AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement | Wenhao Zhou, Jiajun Song, Haitao Wang +11 | cs.AI | 2026-10-13 |
| #19 | WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution | Hang He, Linting Wang, Guanming Liu +14 | cs.AI | 2026-10-13 |
| #20 | Posterior-Averaged Bellman Flow Matching for Distributional Critics | Zeqiao Li, Yijing Wang, Haoyu Wang +2 | cs.LG | 2026-10-13 |
| #21 | Train for Many, Update with One: Improving Multi-Sample Reasoning via Fenchel-Bregman Posterior Learning | Sungjun Lim, Adrian Robert Minut, Nico Carlsen Daheim +3 | cs.LG | 2026-10-13 |
| #22 | ECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution | Xiaoliang Wang, Zhuo Chen, Chuanyang Zheng +8 | cs.AI | 2026-10-13 |
| #23 | World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Models | Junyi Wu, Zekun Li, Chenhongyi Yang +9 | cs.CV | 2026-10-12 |
| #24 | Beyond Successful Play: Diagnosing Opponent Modeling in Large Language Models | Hanbo Xie, Yue Zhao, Robert C. Wilson | cs.AI | 2026-10-12 |
| #25 | D-World: An Explicit World-Language-Action Model with Recursive Self-Improvement under Dual Control | Xuan Wen, Baichao Wang | cs.RO | 2026-10-12 |
| #26 | Relational Learning as World Modeling | Zheyu Zhang, Gjergji Kasneci | cs.LG | 2026-10-12 |
| #27 | Know Yourself and Know Your Neighbour: A Syntactically Informed Self-Supervised Compositional Sentence Representation Learning Framework using a Recursive Hypernetwork | Vasudevan Nedumpozhimana, John Kelleher | cs.CL | 2026-10-12 |
| #28 | Deep Learning-based Mechanical Characterization of Synthetically Generated Plant Fibers under Transverse Compression | Nikolaos Kegkeroglou, Bilal Sabillah, Myrto Inglezou +3 | cs.CV | 2026-10-12 |
| #29 | Trust-Calibrated VLA Policy Post-Training with Evolving Imagination | Wenzhan Li, Yiran Qin, Heng Zhou +3 | cs.RO | 2026-10-12 |
| #30 | Drafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems | Xin Xu, Ke Cheng, Hao Wang +11 | cs.LG | 2026-10-12 |
| #31 | Resample the Answer: Where to Spend Test-Time Compute in Recursive Reasoning | Maxime Illouz | cs.LG | 2026-10-12 |
| #32 | Recursive Environment Scaling for General Long-Horizon Agents | Lingxiao Jing, Zhengbo Jiao, Yichen Xiang +10 | cs.AI | 2026-10-12 |
| #33 | LoopQuant: Accurate and Efficient Post-Training Quantization for Looped Transformers | Zhixiong Zhao, Zukang Xu, Xing Hu +3 | cs.LG | 2026-10-12 |
| #34 | BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates | Lijian Li, Yuanpeng He, Yudian Zheng +6 | cs.CV | 2026-10-12 |
| #35 | Heterogeneous Agentic Coevolution | Wenqian Ye, Ziwei Guan, Zi Yang +14 | cs.AI | 2026-10-12 |
| #36 | Probabilistic Forecasting of Wildfire Size Using Conditional Flow Matching | Isaac Lee, Bryan Shaddy, Assad Oberai | cs.LG | 2026-10-11 |
| #37 | Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping | Songze Li, Haoming Gu, Ziyang Gong +11 | cs.CV | 2026-10-11 |
| #38 | RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution | Fan Zhang, Hao Wu, Jinyang Wu +7 | cs.CL | 2026-10-11 |
| #39 | SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications | Yutong Cheng, Haifeng Chen, Peng Gao +1 | cs.AI | 2026-10-11 |
| #40 | From Stages to States: Unified Iterative Reasoning for MLLMs | Chuang Yu, Xuefei Ma, Yuanhao Feng +9 | cs.AI | 2026-10-11 |
| #41 | Screening Collapse under Recursive Synthetic Data | Jia Zhang, Xin Chen | stat.ML | 2026-10-11 |
| #42 | RSI-Anything: Unlocking Recursive Self-Improvement with World Models | Taoyong Cui, Pinxian Zeng, Wanghan Xu +8 | cs.CL | 2026-10-09 |
| #43 | MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents | Jingwei Song, Zhisheng Chen, Bingfan Zeng +5 | cs.RO | 2026-10-09 |
| #44 | Variance-Reduced Policy Gradient is Nearly Minimax-Optimal | Leonardo Cesani, Matteo Papini, Marcello Restelli | cs.LG | 2026-10-09 |
| #45 | Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning | Oriol Corcoll, Qiyao Wei, Ciarán Mark Gilligan-Lee | cs.LG | 2026-10-09 |
| #46 | Desertification Forecasting in Semi-Arid Regions: Using Deep Learning to Probe the Observability Limits of Land Degradation Dynamics | Filipe Moura Da Silva, Cláubio Landney Lima Bandeira | eess.IV | 2026-10-09 |
| #47 | VETR: Execution-Grounded Self-Improving Agent for Symbolic Graphics Reasoning | Yingbo Ma, Kuangshi Ai, Gordon Dai +3 | cs.AI | 2026-10-09 |
| #48 | Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement | Kairui Hu, Siyuan Hu, Fangzhou Hong +2 | cs.RO | 2026-10-08 |
| #49 | Language Models as AI Research World Models | Zijun Wang, Zewen Liu, Minhua Lin +10 | cs.CL | 2026-10-08 |
| #50 | ReSI: Recursive Safety Improvement toward Resistant and Resilient AI | Jingnan Zheng, Dongcheng Zhang, Yi Zhang +10 | cs.CR | 2026-10-08 |