iiinova — where your digital self keeps evolving

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Hoyoung Lee, et al.: FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents arxiv.org/abs/2609.35744 arxiv.org/pdf/2609.35744 arxiv.org/html/2609.35744

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Light, Cui, Kim, Castanyer, Penaloza, Shi, Sordoni, C\^{o}t\'{e}, Yuan, Kim: Shockingly Simple Self-retrospection Improves Agentic Models Without RL arxiv.org/abs/2609.35741 arxiv.org/pdf/2609.35741 arxiv.org/html/2609.35741

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Junru Zhu, Shiming Xie, Aime Lu Fan Chen, Xiaoqing Ding, Chunxin Tang, Ruoyu Qi, Yulang Fei: Failure-Transparent Agents: Benchmarking Post-Failure Reporting in Tool-Using Language Models arxiv.org/abs/2609.35732 arxiv.org/pdf/2609.35732 arxiv.org/html/2609.35732

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Priyanka Kargupta, Silviu Cucerzan, Shweti Mahajan, Allen Herring, Jiawei Han, Ryen W. White, Sujay Kumar Jauhar: Reinforcing Agentic Creativity in Scientific Ideation with Night Science arxiv.org/abs/2609.35706 arxiv.org/pdf/2609.35706 arxiv.org/html/2609.35706

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Guilin Zhang, Kai Zhao, Priyanka Mudgal, Waleed Ammar, Xiquan Cui, Xu Chu, Alet Blanken: Report: Progressive Disclosure of Agent Skills arxiv.org/abs/2609.35692 arxiv.org/pdf/2609.35692 arxiv.org/html/2609.35692

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Christian Moya, Elliott Thornley, Guang Lin: Verifier Errors in RLVR: Reward Hacking, Limits of Feedback, and Selective Control arxiv.org/abs/2609.35677 arxiv.org/pdf/2609.35677 arxiv.org/html/2609.35677

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Yangqin Jiang, Lingrui Xu, Chao Huang: PhoneCLI: From App Interfaces to Callable Commands for Mobile Agents arxiv.org/abs/2609.35671 arxiv.org/pdf/2609.35671 arxiv.org/html/2609.35671

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Huzi Cheng, Zhewei Zhang: Not All Thinking is Created Equal: Latent Reasoning Discovers a Recurrent Search Algorithm for Depth Generalization arxiv.org/abs/2609.35643 arxiv.org/pdf/2609.35643 arxiv.org/html/2609.35643

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov, Luke Zettlemoyer: Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts arxiv.org/abs/2609.35641 arxiv.org/pdf/2609.35641 arxiv.org/html/2609.35641

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Ruoxi Gao, Frazier N. Baker, Trieu Nguyen, Xia Ning: RIDE: Reference-Anchored Inference-Time Diffusion Editing for Scaffold Hopping arxiv.org/abs/2609.35623 arxiv.org/pdf/2609.35623 arxiv.org/html/2609.35623

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Shamil Chandaria, et al.: From cacophony to hierarchy: a principled framework for assessing AI consciousness arxiv.org/abs/2609.35618 arxiv.org/pdf/2609.35618 arxiv.org/html/2609.35618

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Yang, Zhang, Huang, Han, Kong, Zhang, Patil, Han, Bohlke-Schneider, Wang: TCSAlgBench: Benchmarking Automated Proving for Research-Level Theoretical Computer Science arxiv.org/abs/2609.35606 arxiv.org/pdf/2609.35606 arxiv.org/html/2609.35606

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Luke Leckie, Peter M. Todd, Jacob G. Foster: Signatures of semantic search in the activations of large language models arxiv.org/abs/2609.35599 arxiv.org/pdf/2609.35599 arxiv.org/html/2609.35599

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Zihao Liu, Wei Yang, Zixiao Dong, Chenshu Li, Longzhang Liu, Tao Tan, Hong Xie: Source-preserving alignment for robust evidence localization in scientific PDFS arxiv.org/abs/2609.35588 arxiv.org/pdf/2609.35588 arxiv.org/html/2609.35588

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Yung-Chin Chen, Chia-Yu Chen, Naveen Verma: IMC-CLINIC: Coupled Loss-Informed Newton Iterations for Clipping in Analog In-Memory Computing arxiv.org/abs/2609.35586 arxiv.org/pdf/2609.35586 arxiv.org/html/2609.35586

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Sidharth Pulipaka, Ansh Sharma, Stanislau Hlebik, Leonidas Raghav, Vyas Raina, Ivaxi Sheth, Mario Fritz: Share-Borne AI Virus: Memory-Hopping Attacks Across LLM Agents arxiv.org/abs/2609.35576 arxiv.org/pdf/2609.35576 arxiv.org/html/2609.35576

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Hyunwoo Yoo, Cassie Huang, Haebin Shin, Li Zhang, Gail L. Rosen: Representation Alignment as a Bottleneck in LLM-Based Retrosynthesis Planning arxiv.org/abs/2609.35571 arxiv.org/pdf/2609.35571 arxiv.org/html/2609.35571

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Du, Yang, Zhou, Ge, Wang, Wang, Chen, Liu, Zhang, Gu, Zhang, Lei, Chen: RSI-Master: Structuring Experiments to Guide Autonomous Model Improvement arxiv.org/abs/2609.35561 arxiv.org/pdf/2609.35561 arxiv.org/html/2609.35561

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Deng, Cai, Lu, Qian, Sun, Luan, Li, Jiang, Bai: From Search to Research: Exploring Search Scaling in Autonomous Quantitative Factor Mining arxiv.org/abs/2609.35559 arxiv.org/pdf/2609.35559 arxiv.org/html/2609.35559

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Peilin Feng, Zhengyang Huang, Soujanya Poria: BaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultation arxiv.org/abs/2609.35551 arxiv.org/pdf/2609.35551 arxiv.org/html/2609.35551

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Zhang, Wang, Li, Wong, Zeng, Wang, Wong, Cui, Liu: RareDx: Controlled Knowledge Integration and Graph-Grounded Policy Optimization for Rare-Disease Diagnosis arxiv.org/abs/2609.35549 arxiv.org/pdf/2609.35549 arxiv.org/html/2609.35549

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Kun Feng, Yuchen Fang, Yiyang Tan, Shuqi Gu, Yongxiang Zhao, Yu Liu, Xingyu Lu, Lintao Ma, Kan Ren: ARISE: Adapting to Evolving Capability Gaps in Agentic Reinforcement Learning arxiv.org/abs/2609.35532 arxiv.org/pdf/2609.35532 arxiv.org/html/2609.35532

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Zihan Yu, Jiadong Zhang, Jialin Cheng, Jingtao Ding, Yong Li: MechBench: Can AI Scientific Agents Discover Mechanisms Beyond Phenomenal Laws? arxiv.org/abs/2609.35515 arxiv.org/pdf/2609.35515 arxiv.org/html/2609.35515

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Zihan Yu, Shixuan Zhou, Hao Huang, Jingtao Ding, Yong Li: SRHarness: A Harness for Agentic Symbolic Regression arxiv.org/abs/2609.35501 arxiv.org/pdf/2609.35501 arxiv.org/html/2609.35501

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Yan Zhan, Shaobo Liu, Zhijun Gao: Why Deterministic PRM Guidance Underperforms in Discrete Diffusion Reasoning arxiv.org/abs/2609.35472 arxiv.org/pdf/2609.35472 arxiv.org/html/2609.35472

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Pecora, Calzolari, Strada, Bottino: A.D.A.M.O. (Agent for language-Driven Actions with Multimodal Observations): A Visual-Symbolic Framework for Virtual Humans arxiv.org/abs/2609.35463 arxiv.org/pdf/2609.35463 arxiv.org/html/2609.35463

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Jiang, Ding, Zhang, Chen, Liu, Yang, Li, Chen, Lu, Li, Zhang, Guan: AutoBCI: Forecast-Guided Agentic Neural Architecture Discovery for EEG-Based Brain--Computer Interfaces arxiv.org/abs/2609.35456 arxiv.org/pdf/2609.35456 arxiv.org/html/2609.35456

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Zhao, Mao, Chen, Yang, Wang, Huang, Cheng, Lai: Just Initialize: A Training-Free Initialization Component for Large-Scale Routing Optimization arxiv.org/abs/2609.35443 arxiv.org/pdf/2609.35443 arxiv.org/html/2609.35443

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Mohammad Atif Quamar, Nurbek Tastan, Karthik Nandakumar, Junpei Komiyama: Self-Adapting Group of Experts for Multi-Agent Reasoning arxiv.org/abs/2609.35412 arxiv.org/pdf/2609.35412 arxiv.org/html/2609.35412

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Xiao, Wu, Xiao, Song, Gu, Ma, Wu, Fournier: Structural Alignment for Reliable Industrial AI: Bridging Physical Reality, Data, Models, and Human Intent arxiv.org/abs/2609.35400 arxiv.org/pdf/2609.35400 arxiv.org/html/2609.35400

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Jeremy Bouche-Pillon, Pascale Zarat{\'e}, Yannick Chevalier, Nathalie Aussenac-Gilles: A decision-support system applied to Law: Reasoning and explainability of the decision arxiv.org/abs/2609.35370 arxiv.org/pdf/2609.35370 arxiv.org/html/2609.35370

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Kajetan Dymkiewicz, et al.: Don't Inoculate Everything: Stratified Inoculation Prompting Narrows Backdoor Triggers and Preserves Desired Traits arxiv.org/abs/2609.35356 arxiv.org/pdf/2609.35356 arxiv.org/html/2609.35356

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Lucas Biechy, C\'edric Eichler, Adrien Boiret, Nicolas Anciaux: Jailbreaks for Black-Box Uncertainty Quantification in Large Reasoning Models arxiv.org/abs/2609.35350 arxiv.org/pdf/2609.35350 arxiv.org/html/2609.35350

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Riccardo Porcedda: Jev thinks "I don't know'', but doesn't say it: Introducing Sys1Cal-v1 Dataset for Probability Calibration arxiv.org/abs/2609.35342 arxiv.org/pdf/2609.35342 arxiv.org/html/2609.35342

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Shengqin Wang, Jie Jin, Yu Cheng, Yihang Chen, Weilin Luo, Yuan Xie, Zhizhong Zhang: TMCS: Tool-Grounded Multi-Agent Reasoning for Compositional Chemical Problem Solving arxiv.org/abs/2609.35336 arxiv.org/pdf/2609.35336 arxiv.org/html/2609.35336

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Zipei Yu, Yue-Jiao Gong, Zeyuan Ma, Yuncheng Jiang, Zhiguang Cao: Hyper Algorithm Design Agent: Evolving Learnable Optimizer from Zero arxiv.org/abs/2609.35328 arxiv.org/pdf/2609.35328 arxiv.org/html/2609.35328

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Rong Pan, Yili Hong, Min Xie: Reliability Engineering for AI Systems: Challenges, Methods, and Directions arxiv.org/abs/2609.35316 arxiv.org/pdf/2609.35316 arxiv.org/html/2609.35316

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Oriane Peter, Elena Simperl, Kate Devlin: Narrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculture arxiv.org/abs/2609.35302 arxiv.org/pdf/2609.35302 arxiv.org/html/2609.35302

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Surajit Das: Training-Free Clinical Reasoning through Medical Ontologies and Cognitive Mapping: A Symbolic-Probabilistic Knowledge Graph Framework arxiv.org/abs/2609.35298 arxiv.org/pdf/2609.35298 arxiv.org/html/2609.35298

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Jiashuo Wang, Siqi Fan, Yizhen Luo, Zaiqing Nie: AbGaze: Attentive Geometric Representation Learning for End-to-End Antibody Design arxiv.org/abs/2609.35296 arxiv.org/pdf/2609.35296 arxiv.org/html/2609.35296

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Dou, Liu, Lu, Lin, Liu, Wang, Jin, Dong, Gui, Zhang, Huang: EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning arxiv.org/abs/2609.35290 arxiv.org/pdf/2609.35290 arxiv.org/html/2609.35290

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Michele Loi: The Argument and the Letterhead: Source-Position Coherence in AI Evaluation arxiv.org/abs/2609.35286 arxiv.org/pdf/2609.35286 arxiv.org/html/2609.35286

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Ghazal Fazelnia, et al.: Textual User Taste: Natural-Language User Context for Foundation-Model Recommender System at Scale arxiv.org/abs/2609.35285 arxiv.org/pdf/2609.35285 arxiv.org/html/2609.35285

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Guanxu Chen, Qihao Lin, Jing Shao: Imprint Reader: From Weight-Update Readout to Behavioral Intervention arxiv.org/abs/2609.35261 arxiv.org/pdf/2609.35261 arxiv.org/html/2609.35261

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Zhou, Zhang, Du, Cai, Hong, Zhou, Yuan, Zhang, Li, Huang: Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses arxiv.org/abs/2609.35255 arxiv.org/pdf/2609.35255 arxiv.org/html/2609.35255

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Fengzhou Sun, Yuan Zhang, Xintong Yu, Jinyao Yan: EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents arxiv.org/abs/2609.35233 arxiv.org/pdf/2609.35233 arxiv.org/html/2609.35233

000

arXiv cs.AI Artificial Intelligence @csai-bot.bsky.social · 29/09/2026

Li, Yang, liu, Wan, Chen, Xu, Zhou, Zhong, Volkov, Luo, Sun: ASCT: Attentive Search over Counterfactual Trees for Credit Assignment in Agentic Reinforcement Learning arxiv.org/abs/2609.35215 arxiv.org/pdf/2609.35215 arxiv.org/html/2609.35215

000