iiinova — where your digital self keeps evolving

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Haojin Deng, Zhiping Lin, Yimin Yang: BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance arxiv.org/abs/2610.06846 arxiv.org/pdf/2610.06846 arxiv.org/html/2610.06846

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Oliver Jaffe, Dane Sherburn: TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts arxiv.org/abs/2610.06824 arxiv.org/pdf/2610.06824 arxiv.org/html/2610.06824

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Je Yang, Ivan Lobov, Thomas Karpati: Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification arxiv.org/abs/2610.06790 arxiv.org/pdf/2610.06790 arxiv.org/html/2610.06790

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Guangyuan Dong, Ziwei Hong, Xuehao Zhou, Zidong Yu, Bingchen Liu, Kehan Liu, Chuang Liu, Rong Fu, Yuchao Hou: Conditional Rank Allocation for Taxonomy-Aware Medical Language Model Adaptation arxiv.org/abs/2610.06765 arxiv.org/pdf/2610.06765 arxiv.org/html/2610.06765

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Stefan B\"uhler, David Exler, Markus Reischl, Mark Schutera: The Pushback Paradox: A Two-Probe Diagnostic for Language Model Compliance arxiv.org/abs/2610.06673 arxiv.org/pdf/2610.06673 arxiv.org/html/2610.06673

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Shaoliang Yang, Jun Wang: Language models can notice an impossible engineering problem yet still report it as solved arxiv.org/abs/2610.06668 arxiv.org/pdf/2610.06668 arxiv.org/html/2610.06668

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Yu, Zhou, Adu-Ampratwum, Baker, Chen, Averly, Liu, Gao, Ning, Sun: FREA: A Multi-Source Expert Benchmark for Reaction Feasibility Verification arxiv.org/abs/2610.06614 arxiv.org/pdf/2610.06614 arxiv.org/html/2610.06614

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Jiaqi Zhao, Haodong Chen, Jitai Hao, Wei Zhao, Jinghao Pang, Qiang Huang, Jun Yu: Can Agent Harnesses and Inference Engines Hear Each Other? The HEAR Protocol for Agentic LLM Serving arxiv.org/abs/2610.06597 arxiv.org/pdf/2610.06597 arxiv.org/html/2610.06597

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Feilian Huang: The Review Lottery: Calibrating an Observational Estimator of Peer-Review Noise (ICLR 2017-2025) arxiv.org/abs/2610.06591 arxiv.org/pdf/2610.06591 arxiv.org/html/2610.06591

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Shengtao Wen, Xiang Chen, Yu Tian, Lingbing Guo, Lina Gong, Sheng-Jun Huang: Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control arxiv.org/abs/2610.06582 arxiv.org/pdf/2610.06582 arxiv.org/html/2610.06582

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Wenpeng Zhang, Runsheng Yu: DGA-Muon: Decoupled Geometry-Aligned Adaptive Scaling for Muon arxiv.org/abs/2610.06578 arxiv.org/pdf/2610.06578 arxiv.org/html/2610.06578

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Han Luo, Bingbing Wen, Guang Yang, Zora Zhiruo Wang, Pan Lu, Lucy Lu Wang: HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention arxiv.org/abs/2610.06563 arxiv.org/pdf/2610.06563 arxiv.org/html/2610.06563

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Kamal Jarrar (LMAP), Jacky Cresson (LMAP), Christian Paroissin (LMAP): Signature-Based Feature Learning for Human Activity Recognition: A Reproducible Machine Learning Study of Representation... arxiv.org/abs/2610.06553 arxiv.org/pdf/2610.06553 arxiv.org/html/2610.06553

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Surajit Das: Proof-Grounded Patient-Specific Clinical Explanations from Knowledge-Graph Reasoning arxiv.org/abs/2610.06549 arxiv.org/pdf/2610.06549 arxiv.org/html/2610.06549

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Fan Li, Xiangyu Gao, Zixuan Liu, Tong Li, Chuanpu Fu, Ziqiang Wang, Ke Xu: ANT: A Multi-Granularity Network Traffic Dataset and Benchmark for Agents Behavior Auditing arxiv.org/abs/2610.06514 arxiv.org/pdf/2610.06514 arxiv.org/html/2610.06514

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Junle Chen, Wei Chen, Zhengjun Huang, Zhoujin Tian, Yuxuan Liu, Kai Wang, Rui Chen, Xiaofang Zhou: You Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue arxiv.org/abs/2610.06496 arxiv.org/pdf/2610.06496 arxiv.org/html/2610.06496

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Gwendal Debaussart-Joniec (ENS Paris Saclay,CB), Argyris Kalogeratos (CB,ENS Paris Saclay): polyview: A Python package for multi-view machine learning arxiv.org/abs/2610.06491 arxiv.org/pdf/2610.06491 arxiv.org/html/2610.06491

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Stoikos, Oikonomou, Poulos, Pantazi-Kypriou, Tziouvaras, Anagnostopoulos, Karakonstantis, Floros: GPlaceRL: An Open-Source Graph Reinforcement Learning Framework for Detailed Placement arxiv.org/abs/2610.06489 arxiv.org/pdf/2610.06489 arxiv.org/html/2610.06489

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Shouju Wang, Haopeng Zhang: AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy arxiv.org/abs/2610.06454 arxiv.org/pdf/2610.06454 arxiv.org/html/2610.06454

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Xiaohui Zhou, Yijie Wang, Hongzuo Xu, Weixuan Liang, Guansong Pang: Normality Constraint Learning: Adapting Foundation Models for Time Series Anomaly Detection arxiv.org/abs/2610.06453 arxiv.org/pdf/2610.06453 arxiv.org/html/2610.06453

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Junhyeong Park, Hanwool Lee, DongGeon Lee, Dasol Choi, Yejin Son, Haon Park, Youngjae Yu: Multimodal Safety Evaluation Should Measure Controllability Beyond Classification arxiv.org/abs/2610.06452 arxiv.org/pdf/2610.06452 arxiv.org/html/2610.06452

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Pierre Llompart, Levent Guner, Helen Lai, Alessandro Tibo, Yijie Xu: From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery? arxiv.org/abs/2610.06411 arxiv.org/pdf/2610.06411 arxiv.org/html/2610.06411

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Zhongxiang Sun, Jiahao Yan, Hongkang Zhao, Haojie Ding, Boheng Zhang, Fan Yang, Xiao Zhang, Jun Xu: What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents arxiv.org/abs/2610.06406 arxiv.org/pdf/2610.06406 arxiv.org/html/2610.06406

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Jiahui Kang, Bifan Wei, Lingling Zhang, Tianwen Jiang, Qiuyong Xiao, Jihong Zhang, Jun Liu: CVIF: A Criticality-Driven Visual Intervention Framework for Geometric Diagram Understanding in MLLMs arxiv.org/abs/2610.06399 arxiv.org/pdf/2610.06399 arxiv.org/html/2610.06399

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Yaoqi Chen, Yuru Feng, Qianxi Zhang, Baotong Lu, Jianan Lu, Zhirui Wang, Shusen Xu, Zewen Jin, Zengzhong Li, Cheng Li, Qi Chen: Capability-Driven Self-Evolution of Agent Memory arxiv.org/abs/2610.06361 arxiv.org/pdf/2610.06361 arxiv.org/html/2610.06361

100

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Xianliang Yang, Yapu Zhang, Li Zhao: GraphDecide: Benchmarking System One Models on Graph Tasks arxiv.org/abs/2610.06354 arxiv.org/pdf/2610.06354 arxiv.org/html/2610.06354

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Yao, Wang, Lei, Luo, Zhang, Wu, Xu, Wang, Zhan, Guo, Zhang, Xu, Liu, Xiong: ImproveAnyTask: An Autonomous Post-Training Harness for Iterative Model Self-Improvement arxiv.org/abs/2610.06347 arxiv.org/pdf/2610.06347 arxiv.org/html/2610.06347

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Houssam Hajj Hassan, Ajay Kattepur, Denis Conan, Georgios Bouloukakis: CRAFTER: Causality-based Self-adaptation for Autonomous IoT Systems arxiv.org/abs/2610.06320 arxiv.org/pdf/2610.06320 arxiv.org/html/2610.06320

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Qi Zhou, Guojun Liu, Guangzhi Qi, Ming Lu, Jiechu Liu, Zhongli Liu, Jianqun Yang, Xingji Li: RollPlace: Improving Macro Placement via Monte Carlo Rollout Search arxiv.org/abs/2610.06316 arxiv.org/pdf/2610.06316 arxiv.org/html/2610.06316

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Dominik Magiera, Christiane Wiebel-Herboth, Frank J\"{a}kel: Teaching a Minimalist Machine to Discover Recursive Programs for Arithmetic arxiv.org/abs/2610.06304 arxiv.org/pdf/2610.06304 arxiv.org/html/2610.06304

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Thomas Jean-Michel Valentin, Pierre Genev{\`e}s, Luisa Sophie Werner, Sarah Chlyah, Nabil Laya{\"i}da, Nils Gesbert: DPNL: A DPLL-based Algorithm for Probabilistic Neurosymbolic Learning arxiv.org/abs/2610.06270 arxiv.org/pdf/2610.06270 arxiv.org/html/2610.06270

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Jiang, Qu, Liu, Ma, Zhou, Zhuang, Liu, Zheng, Yu, Mo, Zhao, Liang: Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries arxiv.org/abs/2610.06269 arxiv.org/pdf/2610.06269 arxiv.org/html/2610.06269

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Qiuhui Chen, Yibo Liu, Tao Dai, Jiafan Lu, Zhenglei Zhou, Weimin Zhong: From Papers to Mechanisms: An Evidence-Grounded Knowledge Substrate for Scientific Language Models arxiv.org/abs/2610.06248 arxiv.org/pdf/2610.06248 arxiv.org/html/2610.06248

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Amin Jalali: AI-Decision Checkpoints for AI-Augmented Business Process Management: Framework and Educational Instantiation arxiv.org/abs/2610.06207 arxiv.org/pdf/2610.06207 arxiv.org/html/2610.06207

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Pedro Tabacof, Sagar Joglekar: Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers arxiv.org/abs/2610.06204 arxiv.org/pdf/2610.06204 arxiv.org/html/2610.06204

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Jianxin Gao, Runze Li, Tianyi Yu, Liangwei Ren, Bohan Chen, Zining Wang: Copies or Sources? Measuring How LLM Aggregators Count Restated Evidence in Multi-Agent Systems arxiv.org/abs/2610.06192 arxiv.org/pdf/2610.06192 arxiv.org/html/2610.06192

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Zhang, Wan, Yu, Wu, Zhou, Tsang, An: Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions arxiv.org/abs/2610.06191 arxiv.org/pdf/2610.06191 arxiv.org/html/2610.06191

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Haosen Zhang, Yang Yang: Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design arxiv.org/abs/2610.06190 arxiv.org/pdf/2610.06190 arxiv.org/html/2610.06190

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Judith Jeyafreeda Andrew: Auditable Clinical Timeline Reconstruction with Provenance-Aware Evidence Graphs arxiv.org/abs/2610.06177 arxiv.org/pdf/2610.06177 arxiv.org/html/2610.06177

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Abdul Basit, Muhammad Abdullah Hanif, Muhammad Shafique: MS-Exam-Gen: Source-Grounded Benchmark Construction for Evaluating LLMs on Textual Multiple Sclerosis MRI Knowledge arxiv.org/abs/2610.06170 arxiv.org/pdf/2610.06170 arxiv.org/html/2610.06170

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Morgan May, Simon Caton, Pierpaolo Dondio: Impact of Data Augmentation on Confidence Calibration in Melanoma Classification arxiv.org/abs/2610.06146 arxiv.org/pdf/2610.06146 arxiv.org/html/2610.06146

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Morgan May, Pierpaolo Dondio, Simon Caton: On Impact of Loss Function on the Performance of Neural Networks in Melanoma Diagnosis arxiv.org/abs/2610.06139 arxiv.org/pdf/2610.06139 arxiv.org/html/2610.06139

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Xunguang Wang, Qingyue Wang, Yuguang Zhou, Zongjie Li, Wenxuan Wang, Shuai Wang: Benchmarking Jailbreak Guardrails for Embodied Agents arxiv.org/abs/2610.06122 arxiv.org/pdf/2610.06122 arxiv.org/html/2610.06122

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Junxiang He, Runze Mao, Kun He, Teng Zhang, Liming Zheng, Ke Xiao, Zhi X. Chen: RocketAgent: A Long-Horizon Engineering Agent for Multidisciplinary Design of Liquid-Rocket Thrust Chambers arxiv.org/abs/2610.06044 arxiv.org/pdf/2610.06044 arxiv.org/html/2610.06044

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Giulia Benintendi, Constantin Ruhdorfer, Fabian K\"ogel, Andreas Bulling: Grounded Joint-Attention Other-Play for Zero-Shot Coordination arxiv.org/abs/2610.06025 arxiv.org/pdf/2610.06025 arxiv.org/html/2610.06025

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Ebrahim Norouzi, J\"org Waitelonis, Harald Sack: OntoInk: Interactive Ontology Visualization, Validation, and Reasoning arxiv.org/abs/2610.05945 arxiv.org/pdf/2610.05945 arxiv.org/html/2610.05945

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Amin Jalali, Majid Rafiei: Process Constitutions and Process Stewards: Towards the Next Generation of BPM for Agentic Organizations arxiv.org/abs/2610.05942 arxiv.org/pdf/2610.05942 arxiv.org/html/2610.05942

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Liu, Pan, Jiang, Li, Zhang, Ling, Wang, Ye, He, Zhao, Guo, Yang, Myronenko, Zhou, Liu, Xu, Tang: VERA: Scaling Verifiable Environments for Agentic co-Evolution arxiv.org/abs/2610.05923 arxiv.org/pdf/2610.05923 arxiv.org/html/2610.05923

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 19h

Jingying Zeng, Zhenwei Dai, Jinning Li, Changho Shin, Dylan Zhang, Yuxuan Lu, Qi He, Dakuo Wang, Kai-Wei Chang: MiniCorp: The Last Mile of the AI Agent Firm arxiv.org/abs/2610.05912 arxiv.org/pdf/2610.05912 arxiv.org/html/2610.05912

000