Key papers

• AREX: Towards a Recursively Self-Improving Agent for Deep Research (2026)
  Shuqi Lu et al.
  15.65
• Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning (2026)
  Chen Tang et al.
  14.56
• Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning (2026)
  Junyao Yang et al.
  11.77
• KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill (2026)
  Yunxin Li et al.
  10.74
• ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation (2026)
  Qingyu Zhang et al.
  8.24
• H$^2$SD: Hybrid Hindsight Self-Distillation (2026)
  Qiye Cai et al.
  8.24
• Distilling Multi-modal Large Language Models For Autonomous Driving (2025)
  Deepti Hegde, Rajeev Yasarla, Hong Cai, et al.
  6.80
• Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning (2026)
  Jian Hu et al.
  6.72
• A Controlled Study of Attention-Only Transformers (2026)
  Henry Ndubuaku et al.
  5.96
• Phone Segmentation and Recognition through Phonological Activation Mapping (2026)
  Shikhar Bharadwaj et al.
  5.88
• Rosetta: Composable Native Multimodal Pretraining (2026)
  Xiangyue Liu et al.
  5.49
• MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild Photos (2026)
  Leyuan Yu et al.
  5.49
• Test-Time Scaling via Error Localization (2026)
  Rajiv Shailesh Chitale et al.
  5.49
• Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts (2026)
  Valentin J. J. Kreileder et al.
  5.01
• OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets (2026)
  Rheeya Uppaal et al.
  5.01
• HALO: Hybrid Adaptive Latent Reasoning for Language Models (2026)
  Micah Zhang
  5.01
• Augmenting Fundamental Analysis with Large Language Models: A RAG-Based System for Generating Investor Briefs (2026)
  Bartosz Zi\'o{\l}ko et al.
  5.01
• VTaMo: Video-Text Alignment Model for Sign Language Translation (2026)
  Junyi Hu et al.
  5.01
• Complexity-Guided Component-wise Initialization for Language Model Pretraining (2026)
  Konstantin Garbers et al.
  5.01
• Automatic Thematic Indexing of Large Literary Corpora: A Machine Learning Approach to Voltaire's Complete Works (2026)
  Miguel Arana-Catania et al.
  5.01
• Self-Guided Test-Time Training for Long-Context LLMs (2026)
  Xinyu Zhu et al.
  5.01
• HCIG: A Hierarchical Cross-Modal Incongruity Graph Network for Multimodal Sarcasm and Cyberbullying Detection (2026)
  Bhavana Verma et al.
  5.01
• Multi-Mask Diffusion Language Models for Few-Step Generation (2026)
  Sijin Chen et al.
  5.01
• Learning the Arabic Dialect Continuum as a Continuous Space: A Regression Approach to Speaker Origin Prediction (2026)
  Mohamed Aziz Khadraoui et al.
  5.01
• One More Turn, Less Regret: A Regret-Based Multi-Turn Benchmark for LLMs' Clarification Policies (2026)
  Minh Ngoc Ta et al.
  5.01
• IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation (2026)
  Varun Gumma et al.
  4.98
• Watermarking for Proprietary Dataset Protection (2026)
  John Kirchenbauer et al.
  4.39
• When Does In-Context Search Help? A Sampling-Complexity Theory of Reflection-Driven Reasoning (2026)
  Yotam Wolf et al.
  4.39
• Riemannian Geometry for Pre-trained Language Model Embeddings (2026)
  Szczepan Konior et al.
  4.39
• DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation (2026)
  Jordan Painter et al.
  4.39
• FixItFlow: Automated Troubleshooting Guide Generation from Cloud Incidents (2026)
  Srihari Unnikrishnan et al.
  4.39
• Ask Before You Diagnose: Safe-Psych, a Sequential Evaluation Benchmark for LLMs in Psychiatry (2026)
  Oriana Presacan et al.
  4.39
• The Perplexity Trap: When Patent Law Makes Human Writing Look Like AI (2026)
  Anubhab Banerjee
  4.39
• Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution (2026)
  Hironao Nakamura
  4.39
• SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification (2026)
  SingGuard Team
  4.39
• Adaptive Filtering of the KV Cache: Diagnosing and Correcting Structural-Role Bias in LLM Inference (2026)
  Soumil Mandal
  4.39
• Discourse-Aware Policy Analysis with Argumentation: A Hybrid LLM-Symbolic Framework for Disaster Governance (2026)
  Stylianos Loukas Vasileiou et al.
  4.39
• Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases (2026)
  Marcus J. Min et al.
  4.39
• The Refusal Residue: When Probes Catch Alignment Faking and When They Don't (2026)
  Aman Mehta
  4.39
• LLM-as-a-Judge Scores Are Unreliable Optimization Signals in Closed-Loop Table Recognition (2026)
  Donghwan Kim
  4.39
• GFlowRL: Scaling Distribution-Matching RL to Large Language Models (2026)
  Xiaodong Liu et al.
  4.39
• Set-shifting Behavioral Test for Harnessed Agents (2026)
  Ziwei Ye
  4.39
• Data-Efficient Adaptation of LLMs via Attention Head Reweighting (2026)
  Tuomas Oikarinen et al.
  4.39
• DevicesWorld: Benchmarking Cross-Device Agents in Heterogeneous Environments (2026)
  Huatao Li et al.
  4.39
• UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors (2026)
  Dima Galat et al.
  4.39
• Reliability Scales Inversely: Bigger Language Models Compound Mistakes Faster (2026)
  Kushal Chakrabarti
  4.39
• Binding Drift in Multi-Step Tool-Augmented Agents (2026)
  Rahul Suresh Babu et al.
  4.39
• CANDOR: Chance-Calibrated Discordance in Frozen Foundation Encoders (2026)
  Soroosh Tayebi Arasteh et al.
  4.39
• Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning (2026)
  Lizhe Fang et al.
  4.39
• Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance (2026)
  Sinie van der Ben et al.
  4.39
• Post-Training in Time Series Foundation Models: A Unifying Framework (2026)
  Shifeng Xie et al.
  4.39
• Directional Hallucinations: Ideological Drift in News-Grounded LLM Question Answering (2026)
  Chendi Wang et al.
  4.39
• DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making (2026)
  Raffi Khatchadourian
  4.39
• GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries (2026)
  Miguel P. Bento et al.
  4.39
• OPOD: On-Policy Omni Distillation (2026)
  Tong Zhao et al.
  4.39
• Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks (2026)
  Mack Nixon et al.
  4.39
• What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectors (2026)
  Winston Zeng et al.
  3.51
• T^2MLR: Transformer with Temporal Middle-Layer Recurrence (2026)
  Ziyang Cai et al.
  3.51
• Process Reward Informed Tree Rollout for Effective Multi-Turn RL (2026)
  Xintong Li et al.
  3.51
• Real-World Evaluation of an AI Agent Drafting Translational Impact Summaries (2026)
  Mohammad Arvan et al.
  3.51