{"total":426,"rows":[{"id":"2606.14249","title":"HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry","created":"2026-06-12","cited_by_count":47,"area":null},{"id":"2607.08964","title":"Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading","created":"2026-07-09","cited_by_count":31,"area":null},{"id":"2608.05466","title":"Recursive Synthesis for Long-Horizon Terminal Tasks","created":"2026-08-05","cited_by_count":19,"area":null},{"id":"2605.11181","title":"Muon is Not That Special: Random or Inverted Spectra Work Just as Well","created":"2026-05-11","cited_by_count":14,"area":null},{"id":"2607.01233","title":"Measuring the Gap Between Human and LLM Research Ideas","created":"2026-07-01","cited_by_count":10,"area":null},{"id":"2607.20083","title":"Co-Evolving LLM Evaluators and Policies via DynamicRubric","created":"2026-07-22","cited_by_count":10,"area":null},{"id":"2606.12370","title":"Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling","created":"2026-06-10","cited_by_count":9,"area":null},{"id":"2608.18580","title":"FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis","created":"2026-08-19","cited_by_count":9,"area":null},{"id":"2605.06884","title":"Muon with Nesterov Momentum: Heavy-Tailed Noise and (Randomized) Inexact Polar Decomposition","created":"2026-05-07","cited_by_count":8,"area":null},{"id":"2605.15514","title":"RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2605.29559","title":"LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents","created":"2026-05-28","cited_by_count":8,"area":null},{"id":"2607.04422","title":"Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention","created":"2026-07-05","cited_by_count":8,"area":null},{"id":"2608.06352","title":"CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks","created":"2026-08-06","cited_by_count":8,"area":null},{"id":"2605.07363","title":"MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference","created":"2026-05-08","cited_by_count":7,"area":null},{"id":"2605.13329","title":"Tracing Persona Vectors Through LLM Pretraining","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2605.14220","title":"Diagnosing Training Inference Mismatch in LLM Reinforcement Learning via a Zero-Mismatch Reference","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2605.12492","title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2608.16578","title":"Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents","created":"2026-08-17","cited_by_count":6,"area":null},{"id":"2604.27083","title":"Co-Evolving Policy Distillation","created":"2026-04-29","cited_by_count":5,"area":null},{"id":"2605.06654","title":"Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2606.00408","title":"Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism","created":"2026-05-29","cited_by_count":5,"area":null},{"id":"2606.01629","title":"Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation","created":"2026-06-01","cited_by_count":5,"area":null},{"id":"2608.20169","title":"Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection","created":"2026-08-20","cited_by_count":5,"area":null},{"id":"2605.07342","title":"Mage: Multi-Axis Evaluation of LLM-Generated Executable Game Scenes Beyond Compile-Pass Rate","created":"2026-05-08","cited_by_count":4,"area":null},{"id":"2605.18753","title":"DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2605.22432","title":"AMUSE: Anytime Muon with Stable Gradient Evaluation","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2606.00279","title":"Bit-Exact AI Inference Verification Without Performance Tradeoffs","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2606.01286","title":"BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution","created":"2026-05-31","cited_by_count":4,"area":null},{"id":"2606.04058","title":"Spectral Scaling Laws of Muon","created":"2026-06-02","cited_by_count":4,"area":null},{"id":"2606.11502","title":"When Role-playing, Do Models Believe What They Say?","created":"2026-06-09","cited_by_count":4,"area":null},{"id":"2606.20097","title":"HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization","created":"2026-06-18","cited_by_count":4,"area":null},{"id":"2606.27715","title":"Aurora: A Leverage-Aware Spectral Optimizer","created":"2026-06-26","cited_by_count":4,"area":null},{"id":"2606.28356","title":"SafeGEO: Understanding Generative Engine Optimization Risks in Recommendation Agents","created":"2026-06-08","cited_by_count":4,"area":null},{"id":"2608.13417","title":"Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development","created":"2026-08-13","cited_by_count":4,"area":null},{"id":"2608.27409","title":"Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms","created":"2026-08-27","cited_by_count":4,"area":null},{"id":"2609.24812","title":"MSI-Bench: Evaluating Multi-Speaker Voice Interaction for Collaborative AI Agents","created":"2026-09-21","cited_by_count":4,"area":null},{"id":"2605.08553","title":"VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2605.13907","title":"AIS: Adaptive Importance Sampling for Quantized RL","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2605.21463","title":"Mem-$\\pi$: Adaptive Memory through Learning When and What to Generate","created":"2026-05-20","cited_by_count":3,"area":null},{"id":"2605.26046","title":"When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2605.27887","title":"PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Management","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2606.12837","title":"LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling","created":"2026-06-11","cited_by_count":3,"area":null},{"id":"2606.24020","title":"You Don't Need to Run Every Eval","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2606.27153","title":"DMuon: Efficient Distributed Muon Training with Near-Adam Overhead","created":"2026-06-25","cited_by_count":3,"area":null},{"id":"2606.30015","title":"Parametric Skills","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2607.27183","title":"Pangram 4 Technical Report","created":"2026-07-29","cited_by_count":3,"area":null},{"id":"2608.05102","title":"ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment","created":"2026-08-05","cited_by_count":3,"area":null},{"id":"2608.31119","title":"PaperGym: Rubric-Centered Evolution for Research-Plan Generation","created":"2026-08-31","cited_by_count":3,"area":null},{"id":"2609.08977","title":"Multimodal Duplex Interaction Agent","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2609.09090","title":"SPINE: Measuring LLM Sycophancy under Sustained Multi-Turn Pressure","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2605.06615","title":"When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\\ell_1$-norm Lower Bounds","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.19811","title":"LionMuon: Alternating Spectral and Sign Descent for Efficient Training","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2605.22505","title":"Towards Direct Evaluation of Harness Optimizers via Priority Ranking","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2605.26977","title":"Convergence of Spectral Descent for Non-smooth Optimization","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2605.28025","title":"MIRA: A Bilingual Benchmark for Medical Information Response Audit","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2605.29734","title":"HTAM: Hierarchical Transition-Attended Memory for Operator Optimization","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2605.29791","title":"ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.01034","title":"A Finite-Calibration Regime Map for LLM Judge Panels","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2606.02991","title":"A Language Model from 1913: Pretraining on Historical Text","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.03743","title":"Proof-Refactor: Refactoring Generated Formal Proofs into Modular Artifacts","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.05008","title":"M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2606.05112","title":"Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2606.05553","title":"ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2606.06055","title":"HUSH-Bench: Measuring Memory-Use Boundaries for Sensitive History in Conversational Agents","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2606.07441","title":"Sycophantic Praise: Evaluating Excessive Praise in Language Models","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2606.11275","title":"RoVE: Rotary Value Embeddings Attention for Relative Position-dependent Value Pathways","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2606.14560","title":"Free Heavy-Tailed Lunch for Muon: A Theoretical Justification of Empirical Success","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2606.21804","title":"Is Agent Code Less Maintainable Than Human Code?","created":"2026-06-19","cited_by_count":2,"area":null},{"id":"2607.01103","title":"Evaluating Large Language Model Raters for German Open-Response Clinical Questions: A Physician-Annotated Benchmark Study of Agreement, Evaluator Bias, and Abstention","created":"2026-07-01","cited_by_count":2,"area":null},{"id":"2607.09052","title":"COBS: Cumulant Order Block Sparse Attention","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2607.11976","title":"LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2607.17620","title":"PoLoRA: A Preconditioned Orthogonalized LoRA Optimizer","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2607.22614","title":"DynaResize: Runtime GPU Reallocation for Disaggregated LLM Post-Training","created":"2026-06-15","cited_by_count":2,"area":null},{"id":"2607.23777","title":"Scale Weight Decay and Train Better","created":"2026-07-26","cited_by_count":2,"area":null},{"id":"2607.28110","title":"BlueprintRepair: Typed Local Edits for Failed Lean Proof Blueprints","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2608.01662","title":"LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.01913","title":"Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.02148","title":"Douyin Multimodal Embedding Model Technical Report","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.02520","title":"MedPRESS: A Multi-turn Benchmark for Patient-Pressure-Induced Medical Sycophancy in LLMs","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.03779","title":"AgenticVAU: Multi-Agent Explore-Verify Reasoning for Video Anomaly Understanding","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2608.20153","title":"FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2608.20334","title":"Exploring the Performance Frontier of Compact Unified Image Generation Models","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2608.29381","title":"Safe to Resume? Breaking Execution Continuity of Agent Execution via Rollback","created":"2026-08-29","cited_by_count":2,"area":null},{"id":"2609.05309","title":"How Does mHC Use Its Residual Streams? Selective Routing and Near-Identity Mixing","created":"2026-09-04","cited_by_count":2,"area":null},{"id":"2609.11655","title":"Musec: MomentUm SpEctral Clipping for Stable Muon-type Training","created":"2026-09-10","cited_by_count":2,"area":null},{"id":"2609.13141","title":"SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking","created":"2026-09-11","cited_by_count":2,"area":null},{"id":"2609.17360","title":"Same Words, Different Actions: Paired Turn-Taking Evaluation under Rewritten Dialogue Contexts","created":"2026-09-15","cited_by_count":2,"area":null},{"id":"2610.07557","title":"CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?","created":"2026-10-06","cited_by_count":2,"area":null},{"id":"2605.07268","title":"From 0-Order Selection to 2-Order Judgment: Combinatorial Hardening Exposes Compositional Failures in Frontier LLMs","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.07815","title":"OrScale: Orthogonalised Optimization with Layer-Wise Trust-Ratio Scaling","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.26741","title":"MatFormBench: A Benchmarking Evaluation Framework for Target-Driven Materials Formulation","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2605.30443","title":"Cross-Lingual Steering for Figurative Language Generation","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2605.30963","title":"AMix-2: Establishing Protein as a Native Modality in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.01617","title":"EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.03318","title":"Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.03852","title":"FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.04743","title":"TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2606.07502","title":"Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings","created":"2026-06-05","cited_by_count":1,"area":null}],"next_cursor":"100"}