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 |
|---|---|---|---|---|---|
| Finding Blind Spots in AppWorld and WorkArena Task Verifiers Richard Abrich Published: 2026-10-06Area: cs.AICitations: 12 Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E8 / R6 (94%) | 12 |
| FreeEvolve: Learning to Evolve Beyond Fixed Loops Lecheng Kong, Like Hui, Narayanan Sadagopan, Nikos Kanakaris Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E13 / R9 (93%) | - |
| From High Recall to High Utility: Dataset-Adaptive Post-Processing of LLM-Generated Customer Intents Joan Rossello, Leticia Fernandes, Mahesh Viswanathan, Paul Mutawe Published: 2026-10-06Area: cs.AICitations: 13 Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E9 / R8 (91%) | 13 |
| From Probabilities to Decisions: Search and Multi-Teacher Distillation with Jev Mohamad Yazan Sadoun, Sarah Sharif, Yaser Mike Banad Published: 2026-10-06Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E14 / R10 (92%) | 15 |
| From Uncertainty to Action: Learning to Steer LLM Agents Bo Shen, Chenxi Yuan, Guanhua Zhu, Hanwen Li Published: 2026-10-06Area: cs.AICitations: 45 Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E13 / R8 (88%) | 45 |
| Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI Andriy Myronenko, Ang Li, Can Zhao, Daguang Xu Published: 2026-10-06Area: cs.AICitations: 12 Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E10 / R10 (91%) | 12 |
| GeoNatureAgent (GNA): A Framework and Benchmark for Pre-Production Evaluation of Tool-Using Agents on Geospatial and Environmental Tasks Benjamin Zaitchik, Devika Jain, Diego Prieto-Herr谩ez, Gabriel Diaz-Ireland Published: 2026-10-06Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint, safety-evaluation | 2026-10-06 | cs.AI | ai-safety, csai, preprint, safety-evaluation | E8 / R6 (94%) | 15 |
| How Could AI Eliminate Humanity? A Failure-Mode Analysis of Civilizational Risk Krzysztof Sienicki, Miko艂aj Sienicki Published: 2026-10-06Area: cs.AICitations: 3 Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E16 / R13 (95%) | 3 |
| How Fragile Is On-Device Language Model Safety? Localizing Safety-Critical Parameters for Sparse Fault Analysis Christiana Chamon Garcia, Muhammad Zeeshan Karamat Published: 2026-10-06Area: cs.AICitations: 12 Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E10 / R7 (94%) | 12 |
| How Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-Distillation Guangya Hao, Hao Wu, Longyan Tan, Yiting Duan Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | - | - |
| How Well Do LLMs Reason with Noisy Evidence? An Active Visual Reasoning Benchmark Bach Nguyen, Ben Zhou, Hong Anh Nguyen, Khoa Vo Published: 2026-10-06Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E14 / R12 (92%) | 15 |
| Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models Brian Jang, Chenguang Wang, Daniel Evans, Daniel Quigley Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E9 / R8 (92%) | - |
| Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models Brian Jang, Chenguang Wang, Daniel Evans, Daniel Quigley Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E11 / R10 (90%) | - |
| Humanize: Judgement Engineering for Agentic Coding Changye Li, Dongyun Zou, Ligeng Zhu, Sihao Liu Published: 2026-10-06Area: cs.AICitations: 150 Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E16 / R11 (91%) | 150 |
| Humanize: Judgement Engineering for Agentic Coding Changye Li, Dongyun Zou, Ligeng Zhu, Sihao Liu Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E10 / R8 (92%) | - |
| Illusory Pattern Perception Drives Spurious Inference in Large Language Models Meng Zhang, Peihua Mai, Xinbao Qiao, Xinyue Zhou Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E10 / R6 (90%) | - |
| Isotropic Yet Undecodable: The Sequential Content-Sufficiency Gap in Latent-Predictive Text Representations F. P. Harsanti, G. N. Iyer, K. P. Santoso, N. Z. Fadil Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | - | - |
| Justice After Identity: Large Language Models and the View from Everywhere W. Russell Neuman Published: 2026-10-06Area: cs.AICitations: 45 Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E8 / R6 (92%) | 45 |
| LeanPlan: Optimal Planning with LLM-Generated Heuristics and Admissibility Proofs Andr茅 G. Pereira, Augusto B. Corr锚a, Felipe Meneguzzi, Jendrik Seipp Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | - | - |
| Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Bryan Hooi, Jiaying Wu, Jinhang Qiu, Qianyun Guo Published: 2026-10-06Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E10 / R6 (91%) | 15 |
| Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Bryan Hooi, Jiaying Wu, Jinhang Qiu, Qianyun Guo Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | - | - |
| Learning Explainable Representations of Complex Game-playing Strategies Abhijeet Krishnan, Arnav Jhala, Chris Martens, Colin M. Potts Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E10 / R8 (89%) | - |
| Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents Qianhan Feng, Qi Dou, Xiaofan Zhang, Yakun Zhu Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | - | - |
| Learning in Dreams, Winning in Reality: A Continuous Dyna Loop for a Ten-Hero MOBA Jordy Kieto Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | - | - |
| Learning to Outgrow a Theory: Experimental Discovery Beyond the Initial Hypothesis Space Albert Gao, Chunzheng Zhu, Luqi Gong, Qixin Zhang Published: 2026-10-06Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E10 / R8 (95%) | 15 |
| Learning to Report Unsafe Tasks in a Multi-Agent Game Avyay M. Casheekar, Hariganesh Tangirala Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E9 / R5 (91%) | - |
| Learning to Report Unsafe Tasks in a Multi-Agent Game Avyay M. Casheekar, Hariganesh Tangirala Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E7 / R5 (94%) | - |
| LFHE: Local-First Heuristic Evolution for Bounded Local Topology Search in Decentralized Learning with Non-IID Data Yan Gao, Yang Long, Yin-Kuan Liang Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | - | - |
| LOGIC: An LLM Benchmark for Intent-Grounded Change Impact in Aerospace Electrical Systems Abdul Aleem Mohammed, Muhammad Faraz Shoaib, Muhammad Qasim, Muzammil Adnan Shaik Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E8 / R7 (93%) | - |
| LSC-DPO: Learning-Signal-Controlled Direct Preference Optimization Chengjia Feng, Handan Liu, Yang Qu, Yusheng Han Published: 2026-10-06Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-10-06 | cs.AI | ai-safety, csai, preprint | E12 / R9 (93%) | - |