Key papers

• PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models (2026)
  Yueyi Sun et al.
  12.02
• AutoMem: Automated Learning of Memory as a Cognitive Skill (2026)
  Shengguang Wu et al.
  11.71
• Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs (2026)
  Gabrielle Kaili-May Liu et al.
  10.98
• Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel (2026)
  Sietse Schelpe
  9.96
• Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE (2026)
  Haozhan Tang et al.
  9.60
• Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 Recipe (2026)
  Qian Zhao et al.
  8.80
• Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents (2026)
  Changdae Oh et al.
  8.17
• Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification (2026)
  Yunhao Feng et al.
  7.98
• GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity (2026)
  Yong Yi Bay et al.
  7.37
• HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment (2026)
  Shei Pern Chua et al.
  7.37
• CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression (2026)
  Morayo Danielle Adeyemi et al.
  6.91
• ReFreeKV: Towards Threshold-Free KV Cache Compression (2025)
  Xuanfan Ni et al.
  6.60
• AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation (2026)
  Bao Long Nguyen Huu et al.
  5.88
• Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction (2026)
  Mingzhe Du et al.
  5.88
• LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning (2026)
  Matteo Boglioni et al.
  5.49
• Bounded Morality: Defining the Space of Moral Computation (2026)
  Max Kanwal et al.
  5.01
• NeuroCogMap Reveals Cognitive Organization of Large Language Models (2026)
  Zhongxiang Sun et al.
  5.01
• Real-Time Hard Negative Sampling via LLM-based Clustering for Large-Scale Two-Tower Retrieval (2026)
  Ivan Ji (Zihao) et al.
  5.01
• Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization (2026)
  Xuefeng Liu et al.
  5.01
• Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts (2026)
  Valentin J. J. Kreileder et al.
  5.01
• AIriskEval-edu: New Dataset for Risk Assessment in AI-mediated K-12 Educational Explanations (2026)
  Javier Irigoyen et al.
  5.01
• Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring (2026)
  William Hackett et al.
  5.01
• The Dual Nature of LLM Persona: Aggregated Tendencies and Frame-Dependent Geometry (2026)
  Yuan Yuan
  5.01
• How Do I Know What to Say Next? Barenholtz's Autogenerative Theory as an Enrichment of Harrisean Integrationism (2026)
  J. Mark Bishop et al.
  5.01
• Can We Trust LLM's Logic? Quantifying Uncertainty, Coherence, and Robustness via a Graph-Based Framework (2026)
  Riccardo Revalor et al.
  5.01
• Two Axes of LLM Abstention: Answer Correctness and Question Answerability (2026)
  Benedikt J. Wagner
  5.01
• When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability (2026)
  Zongyou Yang et al.
  5.01
• Just Keep Prompting: Evaluating Repetitive Socratic Prompting in VLMs (2026)
  Shayda Moezzi et al.
  5.01
• Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility (2026)
  Nyx Iskandar
  5.01
• Towards Reliable AI-Assisted Analog Design: Template-Constrained LLM Agents for SAR ADC Generation (2026)
  Dimple Vijay Kochar et al.
  5.01
• OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios (2026)
  Chengyu Shen et al.
  5.01
• Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents (2026)
  Dylan Van Mulders et al.
  5.01
• Symbal: Detecting Systematic Misalignments in Model-Generated Captions (2026)
  Maya Varma et al.
  5.01
• Surprisal Theory is Tautological (without Rational Grounding) (2026)
  Ryan Cotterell
  5.01
• Measuring Curriculum Alignment across Topical Coverage, Competency, and Cognitive Depth: A Longitudinal Framework Applied to CS2013 and CS2023 (2026)
  Sherzod Turaev et al.
  4.95
• IHUBERT: Vector-Based Semantic Deduplication and Domain-Balanced Pretraining for Persian Resources (2026)
  Arash Ghafouri et al.
  4.95
• Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software (2026)
  Arastoo Zibaeirad et al.
  4.95
• TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems (2026)
  Qingyun Liu et al.
  4.95
• Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training (2026)
  Jasmine Brazilek et al.
  4.95
• Assert, don't describe: Linguistic features that shift LLM reasoning about animal welfare (2026)
  Jasmine Brazilek et al.
  4.95
• DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models (2026)
  Yuxuan Yang et al.
  4.95
• Synthetic Feature Augmentation Improves Generalization Performance of Language Models (2025)
  Ashok Choudhary et al.
  4.71
• BaRA: Budget-constrained and Reliable Web Data Collection Agent (2026)
  Soojeong Lee et al.
  4.39
• SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction (2026)
  Sin Yu Bonnie Ho et al.
  4.39
• Libra: Training the Environment for Agentic Information Retrieval (2026)
  Xuan Zhao et al.
  4.39
• Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory (2026)
  ZhiShu Jiang et al.
  4.39
• Making Failure Safe: A Constrained, Verifiable Agent Framework for Open-Web Data Collection (2026)
  Bo Chen
  4.39
• Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows (2026)
  Edward Y. Chang et al.
  4.39
• PHREEQC-MCQ-200: A Diagnostic Benchmark for Tool-Augmented Scientific Simulator Agents (2026)
  Ke Zhang et al.
  4.39
• Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences (2026)
  Mark Russinovich et al.
  4.39
• Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflows (2026)
  Jalal Mahmud et al.
  4.39
• Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains (2026)
  Changguo Jia et al.
  4.39
• Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian Workflows (2026)
  Karthikeya Aditya Vissa et al.
  4.39
• Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL (2026)
  Juliette Decugis et al.
  4.39
• Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning (2026)
  Hongyang He et al.
  4.39
• Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Model (2026)
  Junyan Tan et al.
  4.39
• Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing (2026)
  Joshua Penman
  4.39
• Meta-Benchmarks for Financial-Services LLM Evaluation (2026)
  Blair Hudson
  4.39
• Pre-Flight: A Benchmark for Evaluating Large Language Models on Aviation Operational Knowledge (2026)
  Alex Brooker et al.
  4.39
• Atomic Task Graph: A Unified Framework for Agentic Planning and Execution (2026)
  Yue Zhang et al.
  4.39