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 |
|---|---|---|---|---|---|
| FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model Ariel Deng, Gang Wu, Jingxuan Xu, Songwei Yu Published: 2026-09-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-20 | cs.CL | ai-safety, cscl, preprint | E9 / R7 (91%) | - |
| From UNDRR Reports to Event Records: Schema-Constrained LLM Extraction of Georeferenced Disasters Camilla Andreozzi, Phuong-Anh Nguyen-Le, Revati Mani, Zhijing Jin Published: 2026-09-20Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-20 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (93%) | 12 |
| GRACE: Grounded Adversarial Reasoning over Canadian Law Jiakang Xu, Jonathan H. Chan, Udom Silparcha, Wantong Huo Published: 2026-09-20Area: cs.CLCitations: - Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-09-20 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E10 / R9 (92%) | - |
| HaikuS2S: A Cascaded System For Responding In Verse Conrad Schaumburg, Devangi Sharma, Glenda Tan, Shinji Watanabe Published: 2026-09-20Area: cs.CLCitations: 19 Tags: ai-safety, cscl, preprint | 2026-09-20 | cs.CL | ai-safety, cscl, preprint | E13 / R11 (92%) | 19 |
| Impact Is Not Invalidation: Ask About the Claim, Not the Diff Atul Anand Published: 2026-09-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-20 | cs.CL | ai-safety, cscl, preprint | E8 / R5 (91%) | - |
| Knowing When to Trust Images: Reliability-Aware Multi-modal Entity Alignment Chenxiao Li, Dongfang Liu, Dong Nie, Heng Fan Published: 2026-09-20Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-20 | cs.CL | ai-safety, alignment-training, cscl, preprint | E7 / R8 (93%) | - |
| On the Efficiency-Safety Dilemma in Large Reasoning Models Dongjie Yang, Hai Zhao, Xiao Zhou, Xingrui Wang Published: 2026-09-20Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-20 | cs.CL | ai-safety, cscl, preprint | E17 / R7 (90%) | 15 |
| Propose, Verify, Commit: Evidence-Grounded Memory for Long-Horizon Multi-Actor Conversations Lei Shi, Zhihang Yuan, Zihao Lu Published: 2026-09-20Area: cs.CLCitations: 25 Tags: ai-safety, cscl, preprint | 2026-09-20 | cs.CL | ai-safety, cscl, preprint | E21 / R14 (89%) | 25 |
| RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents Fanyu Zhao, Fugen Yao, Guanjun Jiang, Han Zhang Published: 2026-09-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-20 | cs.CL | ai-safety, cscl, preprint | E11 / R9 (92%) | - |
| RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents Fanyu Zhao, Fugen Yao, Guanjun Jiang, Han Zhang Published: 2026-09-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-20 | cs.CL | ai-safety, cscl, preprint | E11 / R7 (92%) | - |
| STEVE: Stabilizing Textual Gradient-Based Prompt Optimization via Error-Driven Refinement and Regularized Verification Haohan Wang, Lijun Yu, Xinzhuo Li, Yifan Shen Published: 2026-09-20Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-20 | cs.CL | ai-safety, cscl, preprint | E9 / R8 (93%) | - |
| AlexandriaX 2026: The First Shared Task on Dialectal Arabic Machine Translation Abdellah El Mekki, AbdelRahim A. Elmadany, Bernard Ghanem, Mo El-Haj Published: 2026-09-19Area: cs.CLCitations: 12 Tags: ai-safety, cscl, preprint | 2026-09-19 | cs.CL | ai-safety, cscl, preprint | E12 / R11 (94%) | 12 |
| Analyzing Public Discourse on Urbanism: Topic Clustering, Sentiment Analysis and Retrieval-Augmented Generation using YouTube Comments Fayeq Jeelani Syed, Jakob Morales, Monica Hegde Published: 2026-09-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-19 | cs.CL | ai-safety, cscl, preprint | E13 / R6 (94%) | - |
| An Iterative LangGraph Agent for Text-to-SQL: Natural Language Access to the Chicago Crime Database Fayeq Jeelani Syed†, Rupesh Swarnakar, Vigneshwar Ravi Rao Published: 2026-09-19Area: cs.CLCitations: 20 Tags: ai-safety, cscl, preprint | 2026-09-19 | cs.CL | ai-safety, cscl, preprint | E14 / R12 (91%) | 20 |
| Auditing Political Alignment in LLM Assistants: Engagement, Stance, and User Identity Joan C. Timoneda Published: 2026-09-19Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-19 | cs.CL | ai-safety, alignment-training, cscl, preprint | E22 / R10 (96%) | - |
| Automatic multimodal UX improvement recommendations from LLM agent user simulations Anu Chowdhury, Bin Wu, Emine Yilmaz, Hossein A. Rahmani Published: 2026-09-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-19 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (91%) | - |
| Block-Sparse Attention with Semantic-Geometric Decoupled Routing Biqing Qi, Bowen Zhou, Feida Zhu, Pengkun Jiao Published: 2026-09-19Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-19 | cs.CL | ai-safety, cscl, preprint | E10 / R8 (89%) | 15 |
| Diagnose, Then Repair: A Two-Stage MQM-Guided Post-Editing Framework for Domain-Specific Machine Translation Ji Hun Wang, Siyu Wu Published: 2026-09-19Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-09-19 | cs.CL | ai-safety, cscl, preprint | E17 / R15 (93%) | 45 |
| From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness Dennis Wei, Jingyi Sun, Nils Feldhus, Pepa Atanasova Published: 2026-09-19Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-19 | cs.CL | ai-safety, alignment-training, cscl, preprint | E10 / R6 (95%) | - |
| From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness Dennis Wei, Isabelle Augenstein, Jingyi Sun, Nils Feldhus Published: 2026-09-19Area: cs.CLCitations: - Tags: ai-safety, alignment-training, cscl, preprint | 2026-09-19 | cs.CL | ai-safety, alignment-training, cscl, preprint | E13 / R10 (95%) | - |
| LLaDA-PRM: A Bidirectional Step-Level Reasoning Evaluator Naihao Deng, Rada Mihalcea, Yiming Feng, Yulong Chen Published: 2026-09-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-19 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (92%) | - |
| Measuring Behavioural Signatures of Large Language Models through Psychometric Profiling Benwei Zhang, Dixin Zhou, Hua Zheng, Jiahui Fu Published: 2026-09-19Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-19 | cs.CL | ai-safety, cscl, preprint | E7 / R6 (91%) | - |
| Chinese Competitive Debating Dataset and Benchmark Haoyuan Li, Jiamou Liu, Pengqian Han, Yi Zhou Published: 2026-09-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (90%) | - |
| CIBuzzBench: A Benchmark for Cross-Lingual Understanding of Chinese Internet Buzzwords Chaozhuo Li, Fanliang Bu, Jiahao Liu, Junyu Lu Published: 2026-09-18Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, cscl, preprint | E12 / R9 (93%) | 15 |
| Consistent Relexicalization of Clinical Documents using Graph-Based Approach Atri Mandal, Dipankar Das, Sandeep Singh, Tushar Shandhilya Published: 2026-09-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (91%) | - |
| Contextual Causality with Large Language Models: A Survey Chengming Hu, Jun Yan, Yiheng Zhao Published: 2026-09-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, cscl, preprint | E12 / R10 (91%) | - |
| DiaVLo: Diagnosing Behaviours of Vision-Language Models Jie Yang, Lorenzo Corti Published: 2026-09-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, cscl, preprint | E17 / R18 (94%) | - |
| Do Personality-Tuned LLMs Make Better Social Agents? Tim Krabbe, Xiaodan Shi Published: 2026-09-18Area: cs.CLCitations: 35 Tags: ai-safety, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, cscl, preprint | E10 / R7 (93%) | 35 |
| Do Student LLMs Inherit OOD Robustness? Invariance-Weighted Distillation for Reliable Knowledge Transfer Dileesha Kannangara, Sanghamitra Dutta Published: 2026-09-18Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, cscl, preprint | E11 / R10 (93%) | - |
| From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers Chun-Nan Chou, Ji-Lun Peng, Yi-Zhen Zhang, Yun-Nung Chen Published: 2026-09-18Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-09-18 | cs.CL | ai-safety, cscl, preprint | E30 / R19 (89%) | 15 |