Key papers

• Program-as-Weights: A Programming Paradigm for Fuzzy Functions (2026)
  Wentao Zhang et al.
  12.75
• AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents (2026)
  Xiangchen Cheng et al.
  12.32
• EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments (2026)
  Zhilin Wang et al.
  12.32
• CausalMix: Data Mixture as Causal Inference for Language Model Training (2026)
  Zinan Tang et al.
  10.60
• Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination (2026)
  Subhadeep Pal et al.
  9.48
• AutoMem: Automated Learning of Memory as a Cognitive Skill (2026)
  Shengguang Wu et al.
  9.35
• OpenForgeRL: Train Harness-native Agents in Any Environment (2026)
  Xiao Yu et al.
  8.86
• PACE: A Proxy for Agentic Capability Evaluation (2026)
  Yueqi Song et al.
  8.24
• Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training (2026)
  Meng Wang et al.
  7.85
• GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity (2026)
  Yong Yi Bay et al.
  7.37
• Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads (2026)
  Aryo Pradipta Gema et al.
  7.34
• Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning (2026)
  Jian Hu et al.
  6.72
• Rosetta: Composable Native Multimodal Pretraining (2026)
  Xiangyue Liu et al.
  5.49
• Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval (2026)
  Jingjing Zhang et al.
  5.49
• StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning (2026)
  Yuan Qing et al.
  5.49
• QuasiMoTTo: Quasi-Monte Carlo Test-Time Scaling (2026)
  Michael Y. Li et al.
  5.49
• Robust for the Wrong Reasons: The Representational Geometry of LLM Robustness to Science Skepticism (2026)
  Minjong Cheon
  5.49
• World Wide Models: Literary Tools for Cultural AI (2026)
  Nina Begus
  5.49
• LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning (2026)
  Matteo Boglioni et al.
  5.49
• Testing Frontier Large Language Models' Physics Literacy in Parallel Physical Worlds (2026)
  Dong Zhang
  5.01
• Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations (2026)
  Mehul Damani et al.
  5.01
• Office Comprehension Benchmark (2026)
  Firoz Shaik et al.
  5.01
• TurnNat: Automatic Evaluation of Turn-Taking Naturalness in Dyadic Spoken Dialogue (2026)
  Hao Zhang et al.
  5.01
• MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering (2026)
  Dang Quang Thien Tran et al.
  5.01
• IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs (2026)
  Samir Abdaljalil et al.
  5.01
• Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting (2026)
  Shashank Indukuri et al.
  5.01
• DiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents (2026)
  Tianyi Zhang et al.
  5.01
• PARTREP: Learning What to Repeat for Decoder-only LLMs (2026)
  Andikawati P Widjaja et al.
  5.01
• TUDUM: A Turkish-Thinking Reasoning Pipeline for Qwen3.5-27B (2026)
  Baran Bingol et al.
  5.01
• PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation (2026)
  Peng Yun et al.
  5.01
• Towards a Phonology-Informed Evaluation of Multilingual TTS (2026)
  Sneha Ray Barman et al.
  5.01
• OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets (2026)
  Rheeya Uppaal et al.
  5.01
• SPLIT: Cross-Lingual Empathy and Cultural Grounding in English and Ukrainian LLM Responses (2026)
  Anna Chorna
  5.01
• HaloGuard 1.0: An Open Weights Constitutional Classifier for Multilingual AI Safety (2026)
  Navaneeth Sangameswaran et al.
  5.01
• On the Role of Directionality in Structural Generalization (2026)
  Zichao Wei
  5.01
• Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas (2026)
  Yuxuan Li et al.
  5.01
• Multi-Mask Diffusion Language Models for Few-Step Generation (2026)
  Sijin Chen et al.
  5.01
• The Geometry of Personality: Activation Steering with Jungian Cognitive Functions (2026)
  Liu Zai (University of Glasgow) 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
• SPARQL-LLM: Real-Time SPARQL Query Generation from Natural Language Questions (2025)
  Panayiotis Smeros et al.
  4.80
• Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory (2026)
  ZhiShu Jiang et al.
  4.39
• Destination-Labeled Self-Looping Systems with Dwell: Intrinsic Characterization, Realization Cost, and Recognition (2026)
  Reda Belaiche
  4.39
• An LLM-Based Framework for Intent-Driven Network Topology Design (2026)
  Kholoud El-Habbouli et al.
  4.39
• EPC: A Standardized Protocol for Measuring Evaluator Preference Dynamics in LLM Agent Systems (2026)
  Zewen Liu
  4.39
• Mapping the Evaluation Frontier: An Empirical Survey of the Bias-Reliability Tradeoff Across Eleven Evaluator-Agent Conditions (2026)
  Zewen Liu
  4.39
• Watermarking for Proprietary Dataset Protection (2026)
  John Kirchenbauer et al.
  4.39
• MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Molecules (2026)
  Tong Xu 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
• Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Model (2026)
  Junyan Tan et al.
  4.39
• BOUNDARY_SYNC: Measuring Communication-Induced Representational Coupling in Multi-Agent LLM Systems (2026)
  Zewen Liu
  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
• Pre-Flight: A Benchmark for Evaluating Large Language Models on Aviation Operational Knowledge (2026)
  Alex Brooker et al.
  4.39
• Spec-AUF: Accept-Until-Fail Training under Train-Inference Misalignment for Masked Block Drafters (2026)
  Tianjian Yang et al.
  4.39
• Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing (2026)
  Siyuan Li et al.
  4.39
• Challenges and Recommendations for LLMs-as-a-Judge in Multilingual Settings and Low-Resource Languages (2026)
  A. Seza Do\u{g}ru\"oz et al.
  4.39
• HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures (2026)
  Ziyun Qiao et al.
  4.39
• HNSW with Accuracy Guarantees Using Graph Spanners -- A Technical Report (2026)
  Minghao Li et al.
  4.39