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 |
|---|---|---|---|---|---|
| Memory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoning Bingyu Zhu, Haosen Hong, Jungang Lou, Xueshu Chen Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E10 / R8 (90%) | - |
| Meta$^n$: Recursive Self-Improvement through Emergent Depth Dongyeop Kang, Seungyeon Jwa, Young-Jun Lee, Zae Myung Kim Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | - | - |
| MetaRAG: Belief-Action Aligned Policy Optimization for Agentic RAG Jiamu Wang, Jie Liu, Jinjian Zhang, Linjian Mo Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E16 / R15 (90%) | - |
| More GPUs or a Smaller Cache? Tensor Parallelism versus KV Compression for Memory-Bound LLM Serving Anshu Bansal, Jay Iyer, Mehar Simhadri, Raj Dandekar Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E10 / R6 (95%) | - |
| More Rejective, Not More Discriminative: The Unit of Verification in Pre-Execution LLM Oversight Cheng Yan, Wuyang Zhang, Yuchen Han Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E11 / R7 (92%) | - |
| Neurosymbolic Alignment for Physiologically-Safe Clinical Language Models Abdulhady Abas Abdullah, Erik Cambria, Milena Zivkovic Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-08-25 | cs.AI | ai-safety, alignment-training, csai, preprint | - | - |
| OmniJudge or OmniBias? Diagnosing Multimodal Judges through Balanced, Decoupled Lenses Bing Zhao, Guangzheng Hu, HangRui Hu, Hu Wei Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E10 / R7 (94%) | - |
| OPDSearch+: On-Policy Distillation with RL Refinement for Search-Augmented Reasoning Jingjie Xia, Kaiyan Zhao, Qinglin Ye, Shunchao Zheng Published: 2026-08-25Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E10 / R9 (92%) | 15 |
| Parason: Revealing Subtask and Trial Parallelism in LLM Reasoning Jiaxuan Gao, Ligeng Zhu, Shusheng Xu, Song Han Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | - | - |
| Paritok-4B: Intent-Conditioned Context Compression for Coding Agents Jiayu Shi, Luzhuo Chen Published: 2026-08-25Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E10 / R10 (94%) | 15 |
| Partial Identification under Causal Orders by Linear Programming Alessandro Antonucci, Eric Rossetto Published: 2026-08-25Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E10 / R7 (95%) | 15 |
| PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents De-Chuan Zhan, Han-Jia Ye, Song-Yan Li, Xu-Xiang Zhong Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | - | - |
| PhysElite: How Far Are LLMs from Solving Olympiad-Level Physics Problems? Aixin Shi, Haoyu Cheng, Liyunfeng Chen, Qiufeng Wang Published: 2026-08-25Area: cs.AICitations: 33 Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E12 / R12 (95%) | 33 |
| PhysMLLMs: Spatial Priors for Unified Referring Segmentation and Grounded Reasoning of Images and Videos Bimei Wang, Bin Hu, Bo Han, Hong Peng Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | - | - |
| Pivot-and-Station Multi-Agent Path Finding: Solvability, Complexity, and Algorithms Andrea Di Nezza, Fabio Fagnani, Mihir Patel, Sara Bernardini Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | - | - |
| Poisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems Alejandro Lopez-Lira, Chanyeol Choi, CheolWon Na, Dhagash Mehta Published: 2026-08-25Area: cs.AICitations: - Tags: adversarial-robustness, ai-safety, csai, preprint | 2026-08-25 | cs.AI | adversarial-robustness, ai-safety, csai, preprint | E18 / R18 (91%) | - |
| Preference Data Selection for Mitigating the Alignment Tax in Large Language Models Jianxun Lian, Minsu Kim, Steven Euijong Whang, Xing Xie Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, alignment-training, csai, preprint | 2026-08-25 | cs.AI | ai-safety, alignment-training, csai, preprint | E8 / R6 (92%) | - |
| RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons Bo Liu, Jiawei Cao, Peng Ping, Runyu Wang Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | - | - |
| Real-World Knowledge-Guided Change Data Synthesis for Remote Sensing Chao Pang, Guibo Zhu, Gui-Song Xia, Xiangyu Hao Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E10 / R8 (92%) | - |
| Recursive Agentic Reasoning Jing Xie, Shengxin Zhang, Xiaomin Wu, Xiyang Wu Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E14 / R7 (92%) | - |
| Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses Kaiyuan Chen, Ling Yang, Mengdi Wang, Shuicheng Yan Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | - | - |
| Reflection with Action-Induced Visual Differences for Desktop GUI Agents Chaoyue Niu, Fan Wu, Guihai Chen, Yijie Ma Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E7 / R6 (94%) | - |
| Reinforcement Learning-Guided Evolutionary Policy Optimization for Preference-Adjustable Heterogeneous Agile Earth Observation Satellite Scheduling He Wang, Hui Li, Junyu Wu, Liang Li Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | - | - |
| Relative Time Intervals Representation for Word-level Timestamping with Masked Training Dong Zhang, Guodong Zhou, Quanwei Tang, Shoushan Published: 2026-08-25Area: cs.AICitations: 26 Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E11 / R10 (96%) | 26 |
| RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards Boxuan Zhang, Houcheng Jiang, Junfeng Fang, Qiyong Zhong Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E12 / R11 (94%) | - |
| RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards Boxuan Zhang, Houcheng Jiang, Junfeng Fang, Qiyong Zhong Published: 2026-08-25Area: cs.AICitations: 12 Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E12 / R11 (94%) | 12 |
| ReproAgent: Contract-Guided Paper-to-Code Reproduction Wentao Zhang, Xue Hu, Zeli Su, Zewei Pan Published: 2026-08-25Area: cs.AICitations: 15 Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E9 / R8 (91%) | 15 |
| ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping De-Chuan Zhan, Han-Jia Ye, Jun-Jie Tao, Wei-Xiang Mao Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E7 / R6 (93%) | - |
| Retrieve, Match, Escalate: Accurate and Scalable Product Linking with VLM-Distilled Cross-Encoders and Agentic VLMs Charu Sareen, Elaine Wu, Jian Wang, Kyle MacDonald Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | E10 / R7 (94%) | - |
| Right Diagnoses, Decorative Reasoning:A Perturbation Audit of Medical Chain-of-Thought Jifan Gao, Mengzhu Xu, Xia Jiang, Xi Long Published: 2026-08-25Area: cs.AICitations: - Tags: ai-safety, csai, preprint | 2026-08-25 | cs.AI | ai-safety, csai, preprint | - | - |