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 |
|---|---|---|---|---|---|
| Process Reward Informed Tree Rollout for Effective Multi-Turn RL Changlong Yu, Hongye Jin, Jingbo Shang, Linwei Li Published: 2026-07-17Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E8 / R13 (91%) | 45 |
| ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforcement Learning Binglin Zhou, Nan Zhang, Peng Shi, Rui Zhang Published: 2026-07-17Area: cs.CLCitations: 37 Tags: ai-safety, cscl, preprint | 2026-07-17 | cs.CL | ai-safety, cscl, preprint | E13 / R11 (91%) | 37 |
| Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models Dongyub Jude Lee, Heuiseok Lim, Jungseob Lee, Seungyoon Lee Published: 2026-07-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E10 / R6 (94%) | - |
| Controlled Reformulation Testing for Logical Consistency in Large Language Models Alan Chen, Alexander Gu Published: 2026-07-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E16 / R9 (95%) | - |
| Dialogue Summarization with Emotion Dynamics Using Topic- and Participant-Centric Decomposition Linyun Xiang, Mark Neerincx, Stephanie Tan Published: 2026-07-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E18 / R16 (96%) | - |
| Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents Dirk Van den Poel, Dylan Van Mulders, Matthias Bogaert Published: 2026-07-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E14 / R11 (93%) | - |
| Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents Dirk Van den Poel, Dylan Van Mulders, Matthias Bogaert Published: 2026-07-16Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E20 / R23 (92%) | 15 |
| Harnessing LLMs for Reliable Academic Supervision: A Comparative Study Akash Raj Published: 2026-07-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E23 / R21 (95%) | - |
| Harnessing LLMs for Reliable Academic Supervision: A Comparative Study Akash Raj Published: 2026-07-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E10 / R9 (94%) | - |
| In-Place Tokenizer Expansion for Pre-trained LLMs Aditya Tadimeti, Alberto Cabrera, Alexander Amini, Jimmy T. H. Smith Published: 2026-07-16Area: cs.CLCitations: 28 Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E9 / R10 (96%) | 28 |
| Large Language Models as Unified Multimodal Learners for Clinical Prediction Ajay Madhavan Ravichandran, Aljoscha Burchardt, Bilgin Osmandoja, Klaus Netter Published: 2026-07-16Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E15 / R13 (90%) | 45 |
| Latent Trajectory Discrimination for AI-Generated Text Detection Christopher Buratti, Davide Traini, Domenico Ursino, Federica Parlapiano Published: 2026-07-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E6 / R6 (94%) | - |
| Mask-Aware Policy Gradients for Diffusion Language Models Adam Klivans, Haran Raajesh, Kulin Shah, Philipp Kr盲henb眉hl Published: 2026-07-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E8 / R6 (95%) | - |
| OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios Chengyu Shen, Chong Chen, Gangtao Xin, Guojie Zhu Published: 2026-07-16Area: cs.CLCitations: 28 Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E44 / R10 (91%) | 28 |
| SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions Chong Luo, J眉rgen Schmidhuber, Wenyi Wang, Yasheng Sun Published: 2026-07-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E12 / R8 (92%) | - |
| Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution Annette Hautli-Janisz, Artur Romazanov, Ramon Ruiz-Dolz, Zlata Kikteva Published: 2026-07-16Area: cs.CLCitations: 15 Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E24 / R19 (96%) | 15 |
| Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution Annette Hautli-Janisz, Artur Romazanov, Ramon Ruiz-Dolz, Zlata Kikteva Published: 2026-07-16Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E15 / R11 (92%) | 45 |
| T^2MLR: Transformer with Temporal Middle-Layer Recurrence Sanjeev Arora, Xingyu Zhu, Yihe Dong, Yinghui He Published: 2026-07-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E13 / R11 (92%) | - |
| T^2MLR: Transformer with Temporal Middle-Layer Recurrence Sanjeev Arora, Xingyu Zhu, Yihe Dong, Yinghui He Published: 2026-07-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E8 / R8 (93%) | - |
| The Misclassification of Autistic Writing as AI-Generated Matthew C. Kelley, Summer Chambers Published: 2026-07-16Area: cs.CLCitations: 43 Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E8 / R5 (88%) | 43 |
| Verbalizable Representations Form a Global Workspace in Language Models Adam Pearce, Anna Soligo, Ben Thompson, David Abrahams Published: 2026-07-16Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-16 | cs.CL | ai-safety, cscl, preprint | E11 / R9 (91%) | - |
| DevicesWorld: Benchmarking Cross-Device Agents in Heterogeneous Environments Chen Qian, Fei Huang, Hantao Chen, Huatao Li Published: 2026-07-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-15 | cs.CL | ai-safety, cscl, preprint | E8 / R8 (96%) | - |
| Evaluation Ability Does Not Imply Optimization Utility: LLM-as-a-Judge Signals in Closed-Loop Table Recognition Donghwan Kim Published: 2026-07-15Area: cs.CLCitations: 25 Tags: ai-safety, cscl, preprint, safety-evaluation | 2026-07-15 | cs.CL | ai-safety, cscl, preprint, safety-evaluation | E8 / R7 (96%) | 25 |
| HABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective Optimization Abdullah Shaikh, Abdul Samad, Sandesh Kumar, Taha Zahid Published: 2026-07-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-15 | cs.CL | ai-safety, cscl, preprint | E9 / R9 (95%) | - |
| LLM-as-a-Judge Scores Are Unreliable Optimization Signals in Closed-Loop Table Recognition Donghwan Kim Published: 2026-07-15Area: cs.CLCitations: 45 Tags: ai-safety, cscl, preprint | 2026-07-15 | cs.CL | ai-safety, cscl, preprint | E16 / R16 (95%) | 45 |
| Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents Aylin Caliskan, Dong Liu, Edward Sun, Eric Hanchen Jiang Published: 2026-07-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-15 | cs.CL | ai-safety, cscl, preprint | E23 / R21 (96%) | - |
| PReM: Learning What to Preserve and When to Refresh for Context Compression Bohan Yu, Bo Zheng, Chen Han, Chenxi Zhou Published: 2026-07-15Area: cs.CLCitations: - Tags: ai-safety, cscl, preprint | 2026-07-15 | cs.CL | ai-safety, cscl, preprint | E15 / R13 (90%) | - |
| Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel Sietse Schelpe Published: 2026-07-15Area: cs.CLCitations: 18 Tags: ai-safety, cscl, preprint | 2026-07-15 | cs.CL | ai-safety, cscl, preprint | E14 / R12 (96%) | 18 |
| Adaptive Filtering of the KV Cache: Diagnosing and Correcting Structural-Role Bias in LLM Inference Soumil Mandal Published: 2026-07-14Area: cs.CLCitations: 24 Tags: ai-safety, cscl, preprint | 2026-07-14 | cs.CL | ai-safety, cscl, preprint | E14 / R14 (92%) | 24 |
| Breaking Refusal in the First Half: A Mechanistic Study of the Prefill Jailbreak Alex Kwon Published: 2026-07-14Area: cs.CLCitations: - Tags: adversarial-robustness, ai-safety, cscl, preprint | 2026-07-14 | cs.CL | adversarial-robustness, ai-safety, cscl, preprint | E8 / R7 (95%) | - |