Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents Daksh Raghuvanshi, Ved Vedere, Yifan Wang Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E10 / R7 (91%) | - |
| Successive Training Stages and Large Language Model Persuasion: Effects of Misalignment, Supervised Fine-Tuning, and Preference Optimization Antony Dalmiere, Guillaume Auriol, Pascal Marchand, Vincent Nicomette Published: 2026-10-07Area: cs.AICitations: 45 Tags: ai-safety, alignment-training, csai, preprint | 2026-10-07 | cs.AI | ai-safety, alignment-training, csai, preprint | E9 / R7 (93%) | 45 |
| System Switch: When Should a Fast Decision Model Stop and Think? Gian Luca Bailo Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E9 / R9 (92%) | - |
| The AI Evaluation Ecosystem Sang T. Truong, Sanmi Koyejo, Serena Wang, Yash Dave Published: 2026-10-07Area: cs.AICitations: 45 Tags: ai-safety, csai, preprint, safety-evaluation | 2026-10-07 | cs.AI | ai-safety, csai, preprint, safety-evaluation | E8 / R5 (90%) | 45 |
| The Attribution Blind Spot: Layerwise Trajectory Diagnostics for Source Reliance in Retrieval-Augmented Language Models Bo Yang, Chen Ye, Gaolei Li, Meng Han Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E12 / R11 (93%) | - |
| The Handover Problem: Governing Autonomy Transitions in Human-AI Collaboration Antoni Mestre, Manoli Albert, Miriam Gil, Vicente Pelechano Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E10 / R8 (92%) | - |
| The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate Ravil Akhtyamov Published: 2026-10-07Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E8 / R7 (91%) | 15 |
| The Winner's Curse in LLM Self-Improvement Loops: Selection Noise, Lock-in, and Acceptance Rules Litao Hu, Yutong Tang Published: 2026-10-07Area: cs.AICitations: 45 Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E8 / R6 (92%) | 45 |
| Think Before You Paint: Recursive Latent Reasoning for Diffusion Models Jan-Willem van de Meent, Kamil Deja, Ma艂gorzata Grzanka, Pawe艂 Skier艣 Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E9 / R6 (92%) | - |
| TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning Edward Gehringer, Haihua Chen, Haoxuan Zhang, Jianzhe Lin Published: 2026-10-07Area: cs.AICitations: 30 Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E13 / R12 (93%) | 30 |
| UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy Cheng Liu, Dianzhi Yu, Hui Xiang, Ji Zhang Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E8 / R7 (94%) | - |
| Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models Catherine Louise Kling, Daniel Robert Kling Alexander Published: 2026-10-07Area: cs.AICitations: 25 Tags: ai-safety, csai, preprint, safety-evaluation | 2026-10-07 | cs.AI | ai-safety, csai, preprint, safety-evaluation | E12 / R11 (95%) | 25 |
| Verification and Self-Improvement in Agentic AI: Foundations and Limits Chien-Ping Lu Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E7 / R9 (90%) | - |
| We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents Fengning Ou, Jingdi Lei, Kefan Liu, Yelin Luo Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E12 / R9 (93%) | - |
| What the Sleeve Feels: Explainable Machine Learning for Textile Pressure-Based Postural Screening Limon Bin Hossain, Md Sadib Rahman Ananta Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E7 / R5 (94%) | - |
| Where Can a Decision Model Diagnose HVAC Faults? Reasoning Demand, Physical Representation, and Robustness Under Shift Wooyoung Jung Published: 2026-10-07Area: cs.AICitations: 52 Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E10 / R8 (92%) | 52 |
| Whose Ground Truth? Embracing Ambiguity in Human-Centered AI Georgiana Fryza, Giovanni Leoni, Jakob Mainz, Jingyao Wu Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E12 / R10 (95%) | - |
| World Potential Model: Pretrained World Knowledge as Progress Potentials Hao Xu, Jingqi Tong, Jinyang Wu, Jixin Tang Published: 2026-10-07Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-07 | cs.AI | ai-safety, csai, preprint | E6 / R5 (94%) | - |
| AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails Isha Slavin, Jian Ni, Kushal Chawla, Mann Patel Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E8 / R7 (91%) | - |
| Adaptive Power Sampling for LLM Reasoning Bingcong Li, Bingnan Xiao, Chenhao Yang, Wei Ni Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | - | - |
| AGAR: a reinforcement learning substrate for LLM program evolution Annan Li, Dawei Yin, Dou Shen, Haoran Li Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E7 / R5 (90%) | - |
| Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice Jan-Peter Franke Published: 2026-10-06Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E6 / R5 (92%) | 15 |
| Agentic Semantic Sensing for Resource-Adaptive AI-RAN J. Andrew Zhang, Kai Wu, Nan Yang, Xiaoqi Zhang Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E8 / R6 (93%) | - |
| Agent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts? Alexander Rubinstein, Ankit Sonthalia, Haritz Puerto, Martin Gubri Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | - | - |
| AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory Benjamin Fowlersmith, Chirag Sharma, Karime Maamari Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E7 / R6 (92%) | - |
| Agent Plasticity: Measuring Self-Improvement Through Experience Anirudh Goyal, Anton Bakhtin, Anuj Mahajan, Gabriel Synnaeve Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E9 / R8 (92%) | - |
| An AI-Assisted Formalization of the Poincar茅 Conjecture Axel Delaval, Bin Dong, Chunlei Liu, Jiedong Jiang Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | - | - |
| An Empirical Study of Agent Skills' Downstream Utility Dehai Zhao, Qing Huang, Xiaoxue Ren, Yu Cheng Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E11 / R6 (91%) | - |
| An Empirical Study of Agent Skills' Downstream Utility Dehai Zhao, Qing Huang, Xiaoxue Ren, Yu Cheng Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E52 / R37 (88%) | - |
| AnyBottle: A Recipe to Only Keep the Concepts You Really Need Bernt Schiele, David Steinmann, Hevra Petekkaya, Sukrut Rao Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | - | - |