{"total":163,"rows":[{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815,"area":null},{"id":"2603.20633","title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","created":"2026-03-21","cited_by_count":50,"area":null},{"id":"2511.21689","title":"ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration","created":"2025-11-26","cited_by_count":47,"area":null},{"id":"2603.04370","title":"$\\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge","created":"2026-03-04","cited_by_count":39,"area":null},{"id":"2601.07206","title":"LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing","created":"2026-01-12","cited_by_count":38,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2508.12631","title":"Beyond GPT-5: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing","created":"2025-08-18","cited_by_count":34,"area":null},{"id":"2602.16763","title":"When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation","created":"2026-02-18","cited_by_count":33,"area":null},{"id":"2602.06820","title":"ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training","created":"2026-02-06","cited_by_count":32,"area":null},{"id":"2603.25040","title":"Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale","created":"2026-03-26","cited_by_count":29,"area":null},{"id":"2510.23081","title":"A Survey on LLM Mid-Training","created":"2025-10-27","cited_by_count":21,"area":null},{"id":"2601.22607","title":"From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents","created":"2026-01-30","cited_by_count":21,"area":null},{"id":"2510.05318","title":"BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions","created":"2025-10-06","cited_by_count":19,"area":null},{"id":"2508.04664","title":"Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management","created":"2025-08-06","cited_by_count":18,"area":null},{"id":"2509.23124","title":"Non-Collaborative User Simulators for Tool Agents","created":"2025-09-27","cited_by_count":18,"area":null},{"id":"2512.19920","title":"Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning","created":"2025-12-22","cited_by_count":18,"area":null},{"id":"2511.09148","title":"LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls","created":"2025-11-12","cited_by_count":17,"area":null},{"id":"2604.06185","title":"Benchmarking LLM Tool-Use in the Wild","created":"2026-02-13","cited_by_count":17,"area":null},{"id":"2604.00842","title":"Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants","created":"2026-04-01","cited_by_count":15,"area":null},{"id":"2603.01357","title":"ASTRA-bench: Evaluating Tool-Use Agent Reasoning and Action Planning with Personal User Context","created":"2026-03-02","cited_by_count":14,"area":null},{"id":"2604.26256","title":"DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training","created":"2026-04-29","cited_by_count":14,"area":null},{"id":"2511.13029","title":"AA-Omniscience: Evaluating Cross-Domain Knowledge Reliability in Large Language Models","created":"2025-11-17","cited_by_count":13,"area":null},{"id":"2601.10355","title":"Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text","created":"2026-01-15","cited_by_count":13,"area":null},{"id":"2604.18934","title":"AutomationBench","created":"2026-04-21","cited_by_count":12,"area":null},{"id":"2602.13318","title":"DECKBench: Benchmarking Multi-Agent Frameworks for Academic Slide Generation and Editing","created":"2026-02-10","cited_by_count":11,"area":null},{"id":"2607.08716","title":"Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents","created":"2026-07-09","cited_by_count":11,"area":null},{"id":"2510.04491","title":"Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents","created":"2025-10-06","cited_by_count":10,"area":null},{"id":"2607.20734","title":"LLMs Get Lost in Evolving User Intent","created":"2026-07-22","cited_by_count":10,"area":null},{"id":"2605.16679","title":"CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2607.27453","title":"VAmoS Bench: Voice Agent Simulation Bench","created":"2026-07-29","cited_by_count":7,"area":null},{"id":"2510.18170","title":"AgentChangeBench: A Multi-Dimensional Evaluation Framework for Goal-Shift Robustness in Conversational AI","created":"2025-10-20","cited_by_count":6,"area":null},{"id":"2512.07287","title":"Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory","created":"2025-12-08","cited_by_count":6,"area":null},{"id":"2512.23966","title":"Efficient Context Scaling with LongCat ZigZag Attention","created":"2025-12-30","cited_by_count":6,"area":null},{"id":"2604.12312","title":"CompliBench: Benchmarking LLM Judges for Compliance Violation Detection in Dialogue Systems","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2605.07847","title":"Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors","created":"2026-05-08","cited_by_count":6,"area":null},{"id":"2606.17107","title":"Models Take Notes at Prefill: KV Cache Can Be Editable and Composable","created":"2026-06-14","cited_by_count":6,"area":null},{"id":"2509.21175","title":"Who's Laughing Now? An Overview of Computational Humour Generation and Explanation","created":"2025-09-25","cited_by_count":5,"area":null},{"id":"2603.02540","title":"A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities","created":"2026-03-03","cited_by_count":5,"area":null},{"id":"2605.26321","title":"Anchor: Mitigating Artifact Drift in Agent Benchmark Generation","created":"2026-05-25","cited_by_count":5,"area":null},{"id":"2603.01714","title":"TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2603.01940","title":"CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2605.20520","title":"Open-World Evaluations for Measuring Frontier AI Capabilities","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2607.08186","title":"Hidden Decoding at Scale: Latent Computation Scaling for Large Language Models","created":"2026-07-09","cited_by_count":4,"area":null},{"id":"2608.11323","title":"Deployment Decision Reliability: A Generalizability-Theory Framework for Sizing Long-Horizon Agent Evaluations","created":"2026-08-11","cited_by_count":4,"area":null},{"id":"2601.19773","title":"Strong Reasoning Isn't Enough: Evaluating Evidence Elicitation in Interactive Diagnosis","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2604.00010","title":"Can LLMs Perceive Time? An Empirical Investigation","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2604.00830","title":"Meta-TTL: Meta-Learning Self-Improvement Policies for Language Agents","created":"2026-04-01","cited_by_count":3,"area":null},{"id":"2604.06111","title":"AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2605.12922","title":"When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2605.17172","title":"OpenJarvis: Personal AI, On Personal Devices","created":"2026-05-16","cited_by_count":3,"area":null},{"id":"2606.00341","title":"ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2606.16215","title":"PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2608.19861","title":"PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents","created":"2026-08-20","cited_by_count":3,"area":null},{"id":"2510.20784","title":"A Coherence-Based Measure of AGI","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2601.01739","title":"K-EXAONE Technical Report","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2604.24929","title":"GAIA-v2-LILT: Multilingual Adaptation of Agent Benchmark beyond Translation","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2605.18630","title":"SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science","created":"2026-05-18","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":"2605.25680","title":"Simulating Human Memory with Language Models","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.11079","title":"VISTA: A Versatile Interactive User Simulation Toolkit for Agent Evaluation","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2607.01426","title":"When Should Service Agents Reconsider? Difficulty-Routed Control in Customer-Service Operations","created":"2026-07-01","cited_by_count":2,"area":null},{"id":"2607.07435","title":"RLVP: Penalize the Path, Reward the Outcome","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2607.09739","title":"Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Benchmarks","created":"2026-07-02","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":"2608.03764","title":"GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2608.09666","title":"Open Evaluation Agent: Efficient and Promptable Evaluation of Visual Generative Models","created":"2026-08-10","cited_by_count":2,"area":null},{"id":"2608.20350","title":"How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2609.03966","title":"Interface-Induced Trajectory Censoring","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2609.17985","title":"RideWay: Benchmarking Efficient Task Completion for Tool-Using Language Agents","created":"2026-09-16","cited_by_count":2,"area":null},{"id":"2609.37315","title":"Do Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent Environments","created":"2026-09-29","cited_by_count":2,"area":null},{"id":"2510.22143","title":"Benchmarking and Learning Real-World Customer Service Dialogue","created":"2025-10-25","cited_by_count":1,"area":null},{"id":"2511.22130","title":"Benchmarking In-context Experiential Learning Through Repeated Product Recommendations","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2602.16113","title":"Evolutionary Context Search for Automated Skill Acquisition","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.19877","title":"Super Apriel: One Checkpoint, Many Speeds","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.07247","title":"EnvSimBench: A Benchmark for Evaluating and Improving LLM-Based Environment Simulation","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.17106","title":"HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Pools","created":"2026-05-16","cited_by_count":1,"area":null},{"id":"2605.20873","title":"PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2605.22240","title":"Unlocking Proactivity in Task-Oriented Dialogue","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2605.31308","title":"TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2607.02814","title":"SovereignNegotiation-Bench: Evaluating User-Owned Personal Agents In Delegated Bargaining Under Privacy, Consent, Evidence, And Institutional Pressure","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.18985","title":"Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interaction","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2607.22157","title":"Learning on the Job: Continual Learning from Deployment Feedback for Frozen-Weights Agents","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2608.03499","title":"WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.15089","title":"StateM: Reaching 95.3% Raw Accuracy, or a \\$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling","created":"2026-08-15","cited_by_count":1,"area":null},{"id":"2608.17319","title":"Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2608.17499","title":"Towards Better Agents for Multi-Turn User Interaction: The Next User Turn Is More Than Context","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2608.18136","title":"FraudBench: Stress-Testing Policy-Grounded Banking Agents Against Adaptive Fraud","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2608.20634","title":"AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2608.23941","title":"More Rejective, Not More Discriminative: The Unit of Verification in Pre-Execution LLM Oversight","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2608.29397","title":"AlgoWorlds: Benchmarking Tool Use for Global Optimization in Algorithmic Worlds","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2609.01572","title":"From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.10494","title":"IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2609.21187","title":"When Better Turns Do Not Make Better Agents: Diagnosing the Gap Between Next-Turn Metrics and Workflow Success","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2510.13586","title":"Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2512.21010","title":"LLM Swiss Round: Aggregating Multi-Benchmark Performance via Competitive Swiss-System Dynamics","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2601.12740","title":"TreeWriter: AI-Assisted Hierarchical Planning and Writing for Long-Form Documents","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.00456","title":"Benchmarking Agents in Insurance Underwriting Environments","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.11674","title":"Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2604.02315","title":"Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models","created":"2026-04-02","cited_by_count":0,"area":null}],"next_cursor":"100"}