| 1 | Images Talk Back: Guiding MMDiTs by Suppressing Image-to-Text Feedback | Yucheng Yang, Xiaoxiao Sun, Shusheng Yang +2 | cs.CV | 2026-10-09 |
| 2 | X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems | Yeonsung Jung, Zhiyuan Wang, Zifan Wang +5 | cs.AI | 2026-10-09 |
| 3 | Towards Understanding the Training of GFlowNets: A Theoretical Perspective | Rui Hu, Yu Chen, Zhuoran Li +1 | cs.LG | 2026-10-09 |
| #4 | A Baseline Assessment for the Agentic Web Technology Stack | Vagner Figueredo de Santana, Diogo Cortiz | cs.AI | 2026-10-09 |
| #5 | Probabilistic Forecasting of Electric Vehicle Charging in a Time-varying Hierarchical Infrastructure | Guillaume Principato, Yvenn Amara-Ouali, Yannig Goude +2 | stat.AP | 2026-10-09 |
| #6 | One Thing Leads to Another: The Essentials of Time Series Causal Discovery | Kurt Butler, Damian Machlanski, Michael P. J. Camilleri +5 | eess.SP | 2026-10-09 |
| #7 | RegulaTutor: A Theory-Informed Framework for Long-Term Personalized Learning | Yonggang Li, Boqian Han, Rui Sheng +2 | cs.AI | 2026-10-09 |
| #8 | BoundaryEvo: Data-Model Co-Evolution at the Capability Boundary for Long-Chain Reasoning Distillation | Jiaming Su, Suorong Yang, Xudong Li +2 | cs.AI | 2026-10-09 |
| #9 | JANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World Models | Mengdi Liu, Chenghao Jia, Hong Chang +3 | cs.AI | 2026-10-09 |
| #10 | LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management | Songtao Huang, Zhijie Zhong, Xiaohan He +8 | cs.AI | 2026-10-09 |
| #11 | Evolving Creatives with Clicks: CTR-Driven Advertising image Editing via Attribute Disentanglement and Preference Alignment | Xu Zhang, Haohan Wang, Zheng Zhang +9 | cs.CV | 2026-10-09 |
| #12 | Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents | Ziang Ye, Wentao Shi, Lei Chen +7 | cs.AI | 2026-10-09 |
| #13 | Evo$^2$: Evolving the Evolver through Weight-Harness Co-Evolution | Chejian Xu, Shujian Zhang, Wenxuan Zhou +5 | cs.CL | 2026-10-09 |
| #14 | EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents | Jie Huang, Yanan Chen, Ruixun Liu +6 | cs.AI | 2026-10-09 |
| #15 | Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training | Suorong Yang, Jiaxin Wang, Jiaming Su +4 | cs.AI | 2026-10-09 |
| #16 | SEEDS: Preview-Guided Evidence Admission for Search Agents | Jiajin Liu, Chenxi Xu, Dongzhe Fan +2 | cs.CL | 2026-10-09 |
| #17 | DeFiRank: Federated Pairwise Ranking for Governance in Decentralized Financial Networks | Zahra Batool, Michael Duchesne, Kaiwen Zhang +1 | cs.AI | 2026-10-09 |
| #18 | Temporal Evidence Forests for Long-Horizon Multi-Party Conversational Memory | Junyou Guo, Chongyang Tao, Yan He +2 | cs.CL | 2026-10-09 |
| #19 | Rubric-CEPR: Self-Evolving Image Editing via Reward-Verified Self-Distillation | Ritesh Thawkar, Shubham Patle, Shravan Venkatraman +1 | cs.CV | 2026-10-08 |
| #20 | OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning | Zhongyu Yang, Jiale Tao, Ruitao Chen +9 | cs.CV | 2026-10-08 |
| #21 | ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills | Hongxing Li, Dingming Li, Yixin Li +6 | cs.CV | 2026-10-08 |
| #22 | AgentGarten: Code Worlds for Evolving Agents | Jiawei Chi, Shangchen Miao, Zhiyuan Shi +11 | cs.CV | 2026-10-08 |
| #23 | Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness | Saisab Sadhu, Shreeyans Arora, Pratinav Seth | cs.AI | 2026-10-08 |
| #24 | ReSI: Recursive Safety Improvement toward Resistant and Resilient AI | Jingnan Zheng, Dongcheng Zhang, Yi Zhang +10 | cs.CR | 2026-10-08 |
| #25 | Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents | Xiangyi Zeng, Baihang Liu, Xutong Wang +3 | cs.AI | 2026-10-08 |
| #26 | EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution | Yanning Dai, Yuhui Wang, Nanbo Li +2 | cs.AI | 2026-10-08 |
| #27 | Agentic-TTT: Training test-time policy for test-time training | Jiahao Lu, Mohan Kankanhalli | cs.LG | 2026-10-08 |
| #28 | MetaOPD: Meta-Learned Token Weighting for On-Policy Distillation | Zipeng Wang, Xinpeng Dong, Yuefan Wang +6 | cs.AI | 2026-10-08 |
| #29 | Skill-V: Verifiable Self-Evolving Skill Library for Interactive Agents | Jie Ma, Zhipeng Qian, Yufei Ma +6 | cs.CV | 2026-10-08 |
| #30 | MAP4CS: A Multi-dimensional Data Pruning Framework for Efficient Code Retriever Fine-tuning | Yuxuan Chen, Mingwei Liu, Guangsheng Ou +4 | cs.SE | 2026-10-08 |
| #31 | Harness Evolution Hits a Ceiling: When Weight Training Should Begin | Yuan Tian, Bing Hu, Hao Wang +2 | cs.AI | 2026-10-08 |
| #32 | Evidence-Traceable Dynamic Interviewer Architecture for Expertise-Adaptive Qualitative Interviews Using Local LLMs | Aisvarya Adeseye, Jouni Isoaho, Adeyemi Adeseye +2 | cs.AI | 2026-10-08 |
| #33 | Incremental Open-Ended Deep Research with Structured Harness | Meilin Chen, Hongyuan Bao | cs.CL | 2026-10-08 |
| #34 | SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction | Hexuan Deng, Yue Wang, Wenyu Jiang +13 | cs.CL | 2026-10-08 |
| #35 | Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds | Yisen Gao, Yue Guo, Qing Zong +2 | cs.AI | 2026-10-08 |
| #36 | From Chain-of-Thought to Loops: Non-Autoregressive Latent Reasoning via Looped Transformers | Gerard Grau García, Arnau Padrés Masdemont, Niccolò Grillo +3 | cs.AI | 2026-10-08 |
| #37 | Who Verifies the Verifier? Co-Evolving Inspectable Graders with Self-Improving Agents | Xing Zhang, Guanghui Wang, Yanwei Cui +4 | cs.AI | 2026-10-08 |
| #38 | From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning | Fengyuan Liu, Yue Wang, Hangxi Guo +4 | cs.LG | 2026-10-08 |
| #39 | AdaptEvo: Adaptive Agent Learning with Evolving Supervision | Shijun Wan, Jiancong Xie, Hang Xu +7 | cs.CL | 2026-10-08 |
| #40 | SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning | Wei Yang, Shawn Li, Yuehan Qin +8 | cs.AI | 2026-10-08 |
| #41 | EvoSim: Learning to Model, Modeling to Learn | Yun-Wei Song, Jinkai Tao, Jun-Dong Zhang +3 | cs.AI | 2026-10-08 |
| #42 | DynaTE: Accelerating Diffusion LLMs via Dynamic Token Execution | Minghan Jiang, Jiayi Wang, Shuaiting Li +2 | cs.AR | 2026-10-08 |
| #43 | Attributing HOW, Not Just WHICH: Counterfactual Response Trajectories for Diffusion Models | Haoqian Zhang, Ziyuan Yang, Zerui Shao +1 | cs.CV | 2026-10-08 |
| #44 | VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning | Meng Lu, Ligeng Zhu, Olivia Xiao +8 | cs.CV | 2026-10-07 |
| #45 | Learning infinite context windows in recurrent architectures via spatial neural computing | Aleix Salvador-Pomarol, Arthur N. Montanari, Earl K. Miller +2 | cs.LG | 2026-10-07 |
| #46 | EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution | Python Song, Zhixuan Liang, Kelsey Fu +3 | cs.AI | 2026-10-07 |
| #47 | Pathwise Information Certificates for Decentralized Adaptive Sensing | Theodoros Tsiligkaridis | cs.IT | 2026-10-07 |
| #48 | OOM-RL II: Reality Is an Oracle, Not a Debugger Provenance-Constrained Diagnosis in Continually Evolving Agent-Engineered Systems | Kun Liu, Liqun Chen | cs.AI | 2026-10-07 |
| #49 | TestGRAD: Evolving Test Suites via Failure Pattern Momentum for SWE-Agent Ensemble | Pengfei He, Jiayuan Zhou, Shaowei Wang +1 | cs.SE | 2026-10-07 |
| #50 | VideoEvolve: Co-Evolving Memory and Retrieval for Long Video Understanding | Yongchao Xu, Bowen Ye, Jiefeng Gan +5 | cs.CV | 2026-10-07 |