Key papers

• AgenticDataBench: A Comprehensive Benchmark for Data Agents (2026)
  Zhaoyan Sun et al.
  11.22
• H$^2$SD: Hybrid Hindsight Self-Distillation (2026)
  Qiye Cai et al.
  8.57
• NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs (2026)
  Jiarong Zhao et al.
  7.96
• Office Comprehension Benchmark (2026)
  Firoz Shaik et al.
  5.01
• A global predicted-fMRI drive signal from TRIBE does not predict YouTube replay heatmaps (2026)
  Barada Sahu et al.
  5.01
• PARTREP: Learning What to Repeat for Decoder-only LLMs (2026)
  Andikawati P Widjaja et al.
  5.01
• PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation (2026)
  Peng Yun et al.
  5.01
• Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization (2026)
  Jan Drchal
  5.01
• On the Role of Directionality in Structural Generalization (2026)
  Zichao Wei
  5.01
• Measuring Reward-Seeking via Contrastive Belief Updates (2026)
  Axel H{\o}jmark et al.
  5.01
• The Storyteller in the Model: Narrative Pattern Inheritance, Escalation Dynamics, and Alignment Governance in LLMs (2026)
  Adam Rigby et al.
  5.01
• Semantic Field Theory: Historical Origin, Higher-Order Interaction, and Stabilized Semantic Inference (2026)
  Dimitris Vartziotis
  5.01
• RE-AD: Real-Time Requirement Adherence for Data Labeling (2026)
  Siddarth Malreddy et al.
  5.01
• The Geometry of Personality: Activation Steering with Jungian Cognitive Functions (2026)
  Liu Zai (University of Glasgow) et al.
  5.01
• Surprisal Theory is Tautological (without Rational Grounding) (2026)
  Ryan Cotterell
  5.01
• Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery (2026)
  Yuan Si et al.
  4.39
• Black-Box Inference of LLM Architectural Properties with Restrictive API Access (2026)
  Christopher Ellis et al.
  4.39
• On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain (2026)
  Atsuki Yamaguchi et al.
  4.39
• Multi-Head Recurrent Memory Agents (2026)
  Jiatong Li et al.
  4.39
• Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing (2026)
  Joshua Penman
  4.39
• Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysis (2026)
  Jiatong Li et al.
  4.39
• Bayesian Sparse Low-Rank Adaptation for Large Language Model Uncertainty Estimation (2026)
  Jijie Zhang et al.
  4.39
• What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates (2026)
  Arman Ghaffarizadeh et al.
  4.39
• AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows (2026)
  Tejas Singh Anand et al.
  4.39
• Cross-Dialect Generalization Without Retraining: Benchmarks and Evaluation of Schema-Derived Constrained Decoding for MLIR (2026)
  Plawan Kumar Rath
  4.39
• MUX: Continuous Reasoning via Multiplexed Tokens (2026)
  Ayhan Suleymanzade et al.
  4.39
• EmoEUS: Uncertainty Supervision for Multimodal Emotion Recognition in Conversation (2026)
  Zilong Huang et al.
  4.39
• Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs (2026)
  Seunghyun Lee et al.
  4.39
• CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability (2026)
  Pratinav Seth et al.
  4.39
• Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs'Hallucinations (2026)
  Xinyue Fang et al.
  4.39
• Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling (2026)
  Phillip Howard et al.
  4.39
• Automating Formal Verification with Agent-Guided Tree Search (2026)
  Leo Yao
  4.27
• Score Based Error Correcting Code Decoder (2026)
  Alon Helvits et al.
  4.27
• Proving the Coding Interview: A Benchmark for Formally Verified Code Generation (2025)
  Quinn Dougherty and Ronak Mehta
  4.25
• Theoria: Rewrite-Acceptability Verification over Informal Reasoning States (2026)
  Michael Saldivar et al.
  3.51
• Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training (2026)
  Zijian Zhang et al.
  3.51
• ESC: Emotional Self-Correction for Reliable Vision-Language Models (2026)
  Tien-Huy Nguyen et al.
  3.51
• Online Safety Monitoring for LLMs (2026)
  Mona Schirmer et al.
  3.51
• Automated Compliance Mapping in Cloud Security with Domain-Adapted Sentence Transformers (2026)
  John Bianchi et al.
  3.51
• On the feasibility of dependency parsing of non-human sequences without a gold standard. Is evaluation possible in other species? (2026)
  Ramon Ferrer-i-Cancho et al.
  3.51
• Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragments (2026)
  Shuoming Zhang et al.
  3.51
• A Classifier That Teaches Itself: Self-Improving, Frozen-gate Training (SIFT) for Dynamic Document Classification (2026)
  Bogdan Raduta et al.
  3.51
• Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains (2026)
  Liam Swayne
  3.51
• Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning (2026)
  Zijie Liu et al.
  3.51
• LatentMT: Machine Translation with Latent Reasoning (2026)
  Wei-Rui Chen et al.
  3.51
• Verifiable Self-Evolution for Open-Ended Dialogue Skills via Future-Feedback Prediction (2026)
  ChaoJin Zhao et al.
  3.51
• Translation as Augmentation: Effect of Translated Data on Assessment of Difficulty (2026)
  Yiheng Wu et al.
  3.51
• Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning (2026)
  Aixiu An et al.
  3.51
• The Price of Reasoning: Cost-Quality Tradeoffs in Reinforcement Learning for Neural Machine Translation (2026)
  Michael Jungo et al.
  3.51
• Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills (2026)
  Chia-Yi Hsu et al.
  3.39
• ReasonIR: Training Retrievers for Reasoning Tasks (2025)
  Rulin Shao et al.
  2.76
• One mechanism for many mental spaces: a shared router over a value slot in language models (2026)
  Oliver Steele et al.
  2.00
• Optimization Is Not All You Need (2026)
  Minh Hua et al.
  2.00
• RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning (2026)
  Yanqiao Zhu et al.
  2.00
• MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination (2026)
  Joss Armstrong
  1.89
• Efficient Software Vulnerability Detection Using Transformer-based Models (2026)
  Sameer Shaik et al.
  1.83
• CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe (2026)
  Tara Saba et al.
  1.83
• Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels (2026)
  Yifan Zhao et al.
  1.83
• Hierarchical Embedding Fusion for Retrieval-Augmented Code Generation (2026)
  Nikita Sorokin et al.
  1.78
• scicode-lint: Detecting Methodology Bugs in Scientific Python Code with LLM-Generated Patterns (2026)
  Sergey V. Samsonau
  1.78