{"total":85,"rows":[{"id":"2608.27454","title":"WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution","created":"2026-08-27","cited_by_count":12,"area":null},{"id":"2609.30243","title":"JevOut: Natural Context Can Flip Decision Models","created":"2026-09-24","cited_by_count":4,"area":null},{"id":"2607.23806","title":"A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever","created":"2026-07-26","cited_by_count":2,"area":null},{"id":"2608.10108","title":"MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memory","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2608.13482","title":"Synthetic Persona Pretraining: Alignment from Token Zero","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2608.13966","title":"QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2608.17270","title":"Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2608.26582","title":"J-Zero: Unified Challenger--Solver--Judge Self-Evolution from Zero Data","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2608.27370","title":"Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.19745","title":"Region-Level Policy Optimization for Fine-grained MLLM Perception","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2609.21755","title":"ECG Mirage: Revealing and Mitigating the Underutilisation of ECGs in Vision-Language Models for Clinical Prediction","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2609.23417","title":"Omni2Web: Benchmarking Audiovisual Website Development","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2609.32248","title":"Anytime-Valid LLM Leaderboards via Benchmark-weighted and Block-Factorized e-Processes","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2610.04184","title":"EvalResearchBench: Can AI Agents Design Their Own Evaluations?","created":"2026-10-03","cited_by_count":1,"area":null},{"id":"2608.01112","title":"Fighting Fire with Fire: On the Feasibility of Protecting Exercises Against AI Cheating","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.01409","title":"When Retrieval Helps and Distracts: Evaluating Evidence-Generating LLMs for Biomedical Claim Verification","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.06115","title":"Mind the Gaps: Mixture-of-Minds for Human Simulation","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.06758","title":"Stockmark-Nemotron-3-Nano-Omni-JapanDocReader: Structured Document Parsing via Capability Injection and Forgetting Control","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.09593","title":"MADBench: A Benchmark for Modality-Aware Audio Deepfake Detection","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.14999","title":"RamseyGadgets: A Graph Construction Dataset for LLMs","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.16970","title":"Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.19863","title":"Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.28384","title":"MAP: A Benchmark on Multimodal Accessibility Planning for Real World Places","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.30068","title":"TAKE 85: Testing Audiovisual filmmaKer's intEnt across 85 Hours of Film","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.09054","title":"Training-Free Task Vectors for LLM Behavioral Control","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.19515","title":"LLM-as-an-Improver: Turning Verification into Better Candidates","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22150","title":"ECP-Bench: Benchmarking and Learning Entertainment Content Promotion with Foundation Models","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.24744","title":"World State Generator","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.27175","title":"Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.27176","title":"LeakScale: Estimating the Causal Effect of Benchmark Exposure","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.27385","title":"Forecast Workflow Bench: Evaluating Language-Model Decisions with Budgeted Forecast Tools","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.27669","title":"The Path Matters: Evaluating Small Language Models Beyond Answer Accuracy in KGQA","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.28437","title":"MultiVENT-Raw: A Benchmark for Retrieval and Reasoning over Raw Videos","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.29837","title":"PUBG Ally: A Conversational Embodied Agent as an AI Teammate","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.30167","title":"Do Audio Language Models Hear and Read Distinctive Features Alike?","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.30784","title":"Symbiotic Architecture for Post-Hoc Audio Extension of Frozen Language Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32473","title":"VPEvolve: A Self-Evolving Virtual Process Engineer for Computational Lithography","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32763","title":"Mandela-Bench: Multimodal Models Remember Canonical Images Instead of Seeing Them","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33065","title":"Reading Too Much into Context: Passive Exposure Can Steer LLM Decisions","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33878","title":"Curating Merchant-Matching Training Data with Two Confidence-Gated Local LLM Judges","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34151","title":"Self-Evolving Agents via Likelihood-Guided Tool-Space Optimization","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34284","title":"Over-Personalization Is a Decision Failure: Generation-Induced Apply Bias in LLMs","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34425","title":"Zero-Shot Cue-Grounded Topic Segmentation of Spoken Documents","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34992","title":"Composable Decoding on the Probability Simplex: Theory and Implementation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35036","title":"Persona Following Is Not Selective Control: The Neutrality Gap in LLM User Simulation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36194","title":"Concept Direction Reliability Across Languages with Different Tokenizer Fertility","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36253","title":"Population Fidelity: Evaluating Population Representativeness in LLMs","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36705","title":"JudgeProfile: Understanding and Steering Subjectivity in LLM Judges","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37287","title":"VISTA-Bench: Benchmarking Multilingual Image Translation with Image-Specific Rubrics","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37317","title":"What Comes Next? Omni-StoryBench for Evaluating Story-Grounded Omnimodal Generation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37356","title":"Teaching LLMs to Generate Challenging MILP Instances via Solver Feedback","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37624","title":"Correct, Don't Delete: Mitigating Emergent Misalignment with Corrective Supervision","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37700","title":"Locating Answer-Correctness Signals in Frozen Large Language Models","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37938","title":"Does Local Video Understanding Transfer Across Encounters? The EgoGears Benchmark","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38006","title":"HARISSA: Inference-Time Self-Checks for Efficient and Safe Local Language Model Deployment","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38530","title":"Shifting Mechanisms: How Positional Encoding Choice Shapes In-Context Retrieval","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38603","title":"Aperture: Training-Free Multiscale Concept Bottlenecks for Remote Sensing","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38799","title":"Overlap, Unique and Conflict: Can LLMs Extract What They Can Recognize?","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39661","title":"The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39827","title":"Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical Prior","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01382","title":"Gacha Decoding: Eliciting Diverse Generations Through Instruction Following","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01519","title":"Auto-Formalizing Neuro-Symbolic Predictors","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02001","title":"Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02959","title":"TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04329","title":"Suppressing Pressure, Amplifying Evidence: Self-Guided Attention Steering to Mitigate Sycophancy and Stubbornness","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.04444","title":"Causally Fair Generation with Large Language Models","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.05671","title":"How Should a Prompt Optimizer Spend a Tight Budget? BudgetAPO with Noise-Adaptive Evaluation","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.07019","title":"Calibrated Evidence Inference With a Small, Permissively Licensed Open Model","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.07127","title":"PlaySuite: A Large-Scale Benchmark for Interactive Visual Intelligence","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.08055","title":"Language Carries the Expert's Impression: Instrument-Anchored LLM Judges Transfer Counseling-Quality Assessment and Beat In-Domain Training","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.08162","title":"The Failure Is in the Readout: Fine-Grained Emotion Recognition Benchmarks Measure Elicitation, Not Perception","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.09087","title":"U-Space: Uncovering When and Why Uncertainty Arises in Language Models","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.10114","title":"Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.10738","title":"Lossy Compressive Text Autoencoders","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.10845","title":"Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.10868","title":"Conversational Voice Aesthetic Model with Reinforcement Learning from Human Listeners","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11132","title":"SFT-as-Context Mitigates Forgetting in Supervised Fine-Tuning","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.11736","title":"Towards Unified Evaluation of Prompt Enhancers for Video Generation","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.15415","title":"Sensitivity or Criterion? Measuring and Moving When Language Models Act","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.15894","title":"Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.16942","title":"UA-Bench: Benchmarking Large Audio-Language Models on Underwater Acoustic Recognition","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19157","title":"DivAlgo: A systematic evaluation of algorithmic diversity for code generation models","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19166","title":"Fantastic Metrics and How to Find Them: Meta-Evaluating Metrics for Multi-lingual Style-Personalized Generation","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19238","title":"LLMs program using Reusable and Composable Abstract Representations","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20538","title":"PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}