{"total":64,"rows":[{"id":"2605.27922","title":"Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows","created":"2026-05-27","cited_by_count":57,"area":"agents"},{"id":"2605.10912","title":"WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation","created":"2026-05-11","cited_by_count":37,"area":"agents"},{"id":"2604.26752","title":"GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents","created":"2026-04-29","cited_by_count":34,"area":"agents"},{"id":"2604.08523","title":"ClawBench: Can AI Agents Complete Everyday Online Tasks?","created":"2026-04-09","cited_by_count":33,"area":null},{"id":"2605.12500","title":"SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture","created":"2026-05-12","cited_by_count":32,"area":"mllm"},{"id":"2604.23781","title":"ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents","created":"2026-04-26","cited_by_count":17,"area":"agents"},{"id":"2604.26904","title":"ClawGym: A Scalable Framework for Building Effective Claw Agents","created":"2026-04-29","cited_by_count":15,"area":"agents"},{"id":"2605.22794","title":"MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems","created":"2026-05-21","cited_by_count":13,"area":"agents"},{"id":"2605.14271","title":"Auditing Agent Harness Safety","created":"2026-05-14","cited_by_count":11,"area":"agents"},{"id":"2606.01311","title":"SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories","created":"2026-05-31","cited_by_count":11,"area":"agents"},{"id":"2607.28227","title":"Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents","created":"2026-07-30","cited_by_count":11,"area":"agents"},{"id":"2608.09096","title":"Evo-Bench: Can Language Models Improve Agent Harness?","created":"2026-08-10","cited_by_count":11,"area":"agents"},{"id":"2604.18543","title":"ClawEnvKit: Automatic Environment Generation for Claw-Like Agents","created":"2026-04-20","cited_by_count":8,"area":null},{"id":"2605.15040","title":"Orchard: An Open-Source Agentic Modeling Framework","created":"2026-05-14","cited_by_count":8,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2606.12344","title":"Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks","created":"2026-06-10","cited_by_count":8,"area":null},{"id":"2608.03874","title":"ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?","created":"2026-08-04","cited_by_count":8,"area":"agents"},{"id":"2604.10866","title":"OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation","created":"2026-04-13","cited_by_count":7,"area":"agents"},{"id":"2607.21557","title":"OpenForgeRL: Train Harness-native Agents in Any Environment","created":"2026-07-23","cited_by_count":7,"area":null},{"id":"2605.05980","title":"TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering","created":"2026-05-07","cited_by_count":6,"area":"lr"},{"id":"2605.14678","title":"$\\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2606.14302","title":"Retrospective Progress-Aware Self-Refinement for LLM Agent Training","created":"2026-06-12","cited_by_count":6,"area":"agents"},{"id":"2605.10779","title":"LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments","created":"2026-05-11","cited_by_count":5,"area":"agents"},{"id":"2605.29253","title":"OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2607.09375","title":"Mach-Mind-4-Flash Technical Report","created":"2026-07-10","cited_by_count":4,"area":"agents"},{"id":"2605.14133","title":"ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2606.00579","title":"Sandboxed Coding Agents are Competitive Omni-modal Task Solvers","created":"2026-05-30","cited_by_count":3,"area":"mllm"},{"id":"2606.03889","title":"RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2606.17016","title":"TokenPilot: Cache-Efficient Context Management for LLM Agents","created":"2026-06-15","cited_by_count":3,"area":"agents"},{"id":"2608.25920","title":"Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems","created":"2026-08-26","cited_by_count":3,"area":"lr"},{"id":"2609.11977","title":"Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work","created":"2026-09-04","cited_by_count":3,"area":"agents"},{"id":"2606.22557","title":"MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop","created":"2026-06-21","cited_by_count":2,"area":"agents"},{"id":"2609.25611","title":"Qwen3.8-Omni: Towards Native Omni-Modal Agents","created":"2026-09-22","cited_by_count":2,"area":"agents"},{"id":"2604.22577","title":"QuantClaw: Precision Where It Matters for OpenClaw","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.06731","title":"When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2605.26086","title":"Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2606.02302","title":"SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents","created":"2026-06-01","cited_by_count":1,"area":"agents"},{"id":"2606.19787","title":"ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2607.06008","title":"PolyWorkBench: Benchmarking LLM Agents for Cross-Lingual Long-Horizon Workflows","created":"2026-07-07","cited_by_count":1,"area":"agents"},{"id":"2607.14989","title":"OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios","created":"2026-07-16","cited_by_count":1,"area":"agents"},{"id":"2607.23524","title":"Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis","created":"2026-07-26","cited_by_count":1,"area":null},{"id":"2607.26791","title":"SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"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":"2608.20485","title":"Terminal Agents: A Survey of AI Agents in Command-Line Environments","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2609.24526","title":"ME-VLM: A Unified VLM for Embodied Cognition and Agent Coordination","created":"2026-09-21","cited_by_count":1,"area":"agents"},{"id":"2609.38604","title":"Beyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2605.04624","title":"AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2607.02598","title":"Evaluating Agentic Harness Systems for Autonomous Computational Pathology","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2607.05473","title":"Binocular Gaze Estimation with Single Camera and Single Light Source","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.20597","title":"Testing and Evaluation of Agentic AI Systems In Military Command and Control","created":"2026-08-20","cited_by_count":0,"area":"agents"},{"id":"2609.12394","title":"BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents","created":"2026-09-11","cited_by_count":0,"area":"agents"},{"id":"2609.29892","title":"Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.33772","title":"Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36380","title":"LEGO-Anything: Coding Agents for 3D Scene Reconstruction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36887","title":"WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.38372","title":"Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.38923","title":"GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39068","title":"SparseEngine: Sparse-First Inference Engine","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.13438","title":"Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.14118","title":"ClawLoop: Self-Improving Agents via Harness-Native Training Loop","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.14915","title":"WorkBorne: Discovering Agentic Tasks from Real-World Artifact Transitions","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.14918","title":"SkillForgeBench: Evaluating Agent Reliability Grounded in Agent Skill Specifications","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.17670","title":"Cowork-Gym: Synthesizing Interactive Work Environments at Scale","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18330","title":"AssetForge: Asset-Augmented Task Synthesis for Business Automation Agents","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}