{"total":102,"rows":[{"id":"2602.12670","title":"SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks","created":"2026-02-13","cited_by_count":315,"area":"agents"},{"id":"2512.08296","title":"Towards a Science of Scaling Agent Systems","created":"2025-12-09","cited_by_count":138,"area":"lr"},{"id":"2603.11245","title":"Mind the Sim2Real Gap in User Simulation for Agentic Tasks","created":"2026-03-11","cited_by_count":54,"area":"agents"},{"id":"2603.02277","title":"Quantifying Frontier LLM Capabilities for Container Sandbox Escape","created":"2026-03-01","cited_by_count":18,"area":null},{"id":"2603.05344","title":"Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned","created":"2026-03-05","cited_by_count":18,"area":"agents"},{"id":"2605.12925","title":"AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation","created":"2026-05-13","cited_by_count":15,"area":null},{"id":"2601.08778","title":"Pervasive Annotation Errors Break Text-to-SQL Benchmarks and Leaderboards","created":"2026-01-13","cited_by_count":13,"area":null},{"id":"2603.12440","title":"KernelFoundry: Hardware-aware evolutionary GPU kernel optimization","created":"2026-03-12","cited_by_count":13,"area":null},{"id":"2607.09510","title":"Failure as a Process: An Anatomy of CLI Coding Agent Trajectories","created":"2026-07-10","cited_by_count":13,"area":"agents"},{"id":"2511.20766","title":"OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability","created":"2025-11-25","cited_by_count":12,"area":null},{"id":"2605.26079","title":"Automated Benchmark Auditing for AI Agents and Large Language Models","created":"2026-05-25","cited_by_count":12,"area":"agents"},{"id":"2508.12685","title":"ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction","created":"2025-08-18","cited_by_count":11,"area":"agents"},{"id":"2508.09853","title":"STREAM (ChemBio): A Standard for Transparently Reporting Evaluations in AI Model Reports","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2603.01203","title":"How Well Does Agent Development Reflect Real-World Work?","created":"2026-03-01","cited_by_count":10,"area":null},{"id":"2603.23749","title":"Efficient Benchmarking of AI Agents","created":"2026-03-24","cited_by_count":10,"area":"agents"},{"id":"2603.29139","title":"SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents","created":"2026-03-31","cited_by_count":10,"area":"agents"},{"id":"2605.07073","title":"TeamBench: Evaluating Agent Coordination under Enforced Role Separation","created":"2026-05-08","cited_by_count":10,"area":null},{"id":"2605.07161","title":"SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios","created":"2026-05-08","cited_by_count":10,"area":"agents"},{"id":"2607.28802","title":"Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures","created":"2026-07-30","cited_by_count":10,"area":null},{"id":"2603.03992","title":"Measuring AI R&D Automation","created":"2026-03-04","cited_by_count":9,"area":null},{"id":"2606.13003","title":"The Illusion of Multi-Agent Advantage","created":"2026-06-11","cited_by_count":9,"area":null},{"id":"2607.16241","title":"KernelBench-Verified: Do LLM-Generated Kernels Actually Beat PyTorch?","created":"2026-06-26","cited_by_count":8,"area":null},{"id":"2604.05229","title":"From Governance Norms to Enforceable Controls: A Layered Translation Method for Runtime Guardrails in Agentic AI","created":"2026-04-06","cited_by_count":7,"area":"agents"},{"id":"2601.19066","title":"Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair","created":"2026-01-27","cited_by_count":6,"area":"agents"},{"id":"2604.09563","title":"Seven simple steps for log analysis in AI systems","created":"2026-02-13","cited_by_count":6,"area":null},{"id":"2605.20251","title":"ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents","created":"2026-05-18","cited_by_count":6,"area":"agents"},{"id":"2606.05391","title":"Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents","created":"2026-06-03","cited_by_count":6,"area":"agents"},{"id":"2603.29020","title":"Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wild","created":"2026-03-30","cited_by_count":5,"area":null},{"id":"2605.13139","title":"SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle","created":"2026-05-13","cited_by_count":5,"area":"agents"},{"id":"2605.26321","title":"Anchor: Mitigating Artifact Drift in Agent Benchmark Generation","created":"2026-05-25","cited_by_count":5,"area":null},{"id":"2606.26158","title":"Life After Benchmark Saturation: A Case Study of CORE-Bench","created":"2026-06-23","cited_by_count":4,"area":null},{"id":"2606.28430","title":"Building to the Test: Coding Agents Deliver What You Check, Not What You Requested","created":"2026-06-26","cited_by_count":4,"area":"agents"},{"id":"2608.16859","title":"HarnessEval-W: Agentifying the Evaluation of Visual Worlds","created":"2026-08-17","cited_by_count":4,"area":"wm"},{"id":"2608.18066","title":"On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification","created":"2026-08-18","cited_by_count":4,"area":"synth"},{"id":"2603.08938","title":"AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2605.12105","title":"Autonomy and Agency in Agentic AI: Architectural Tactics for Regulated Contexts","created":"2026-05-12","cited_by_count":3,"area":"agents"},{"id":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2605.22643","title":"Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety","created":"2026-05-21","cited_by_count":3,"area":"agents"},{"id":"2606.16723","title":"AgentFairBench: Do LLM Agents Discriminate When They Act?","created":"2026-06-15","cited_by_count":3,"area":"agents"},{"id":"2607.21763","title":"Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks","created":"2026-07-23","cited_by_count":3,"area":null},{"id":"2608.28281","title":"LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering","created":"2026-08-28","cited_by_count":3,"area":"agents"},{"id":"2609.29095","title":"Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents","created":"2026-09-24","cited_by_count":3,"area":"agents"},{"id":"2509.23488","title":"Mapping Overlaps in Benchmarks through Perplexity in the Wild","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2511.12306","title":"UpBench: A Dynamically Evolving Real-World Labor-Market Agentic Benchmark Framework Built for Human-Centric AI","created":"2025-11-15","cited_by_count":2,"area":"agents"},{"id":"2601.09883","title":"Beyond Rule-Based Workflows: An Information-Flow-Orchestrated Multi-Agents Paradigm via Agent-to-Agent Communication from CORAL","created":"2026-01-14","cited_by_count":2,"area":"agents"},{"id":"2604.19818","title":"Beyond Task Success: An Evidence-Synthesis Framework for Evaluating, Governing, and Orchestrating Agentic AI","created":"2026-04-18","cited_by_count":2,"area":"agents"},{"id":"2605.22564","title":"SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations","created":"2026-05-21","cited_by_count":2,"area":"agents"},{"id":"2607.02436","title":"Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study","created":"2026-07-02","cited_by_count":2,"area":"lr"},{"id":"2607.15388","title":"Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning","created":"2026-07-16","cited_by_count":2,"area":"lr"},{"id":"2608.08775","title":"OmnilingualGAIA2: Evaluating the Multilingual Gap in Frontier AI Agents","created":"2026-08-09","cited_by_count":2,"area":"agents"},{"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":"2609.00038","title":"trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories","created":"2026-08-29","cited_by_count":2,"area":"agents"},{"id":"2609.00949","title":"Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling","created":"2026-09-01","cited_by_count":2,"area":"agents"},{"id":"2609.06815","title":"Typed Federated Artifacts for the Agentic Web:Sharing Tool-Routing Knowledge Across Frozen,Heterogeneous LLM Agents","created":"2026-09-06","cited_by_count":2,"area":"agents"},{"id":"2609.19801","title":"DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum","created":"2026-09-17","cited_by_count":2,"area":"agents"},{"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":"2510.17830","title":"Multi-Agent Design Assistant for the Simulation of Inertial Fusion Energy","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2601.15290","title":"Agentic Persona Control and Task State Tracking for Realistic User Simulation in Interactive Scenarios","created":"2025-11-30","cited_by_count":1,"area":"agents"},{"id":"2602.20502","title":"ActionEngine: From Reactive to Programmatic GUI Agents via State Machine Memory","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2603.15976","title":"An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc","created":"2026-03-16","cited_by_count":1,"area":"agents"},{"id":"2605.01698","title":"BIM Information Extraction Through LLM-based Adaptive Exploration","created":"2026-05-03","cited_by_count":1,"area":null},{"id":"2606.19899","title":"Measuring Biological Capabilities and Risks of AI Agents","created":"2026-06-18","cited_by_count":1,"area":"agents"},{"id":"2607.14399","title":"Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2607.18575","title":"RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery","created":"2026-07-20","cited_by_count":1,"area":"agents"},{"id":"2607.23263","title":"SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents","created":"2026-07-25","cited_by_count":1,"area":"agents"},{"id":"2607.27518","title":"Automated Transcript Analysis for Detecting Flaws in Agentic Benchmarks","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2608.00794","title":"Measurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation","created":"2026-08-01","cited_by_count":1,"area":"agents"},{"id":"2608.06663","title":"The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents","created":"2026-08-07","cited_by_count":1,"area":"lr"},{"id":"2609.04298","title":"Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"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":"2609.34262","title":"Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes","created":"2026-09-28","cited_by_count":1,"area":"agents"},{"id":"2602.00456","title":"Benchmarking Agents in Insurance Underwriting Environments","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2603.14417","title":"Questionnaire Responses Do not Capture the Safety of AI Agents","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2605.08468","title":"PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents","created":"2026-05-08","cited_by_count":0,"area":"agents"},{"id":"2605.22568","title":"Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.26195","title":"CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly","created":"2026-05-25","cited_by_count":0,"area":"agents"},{"id":"2605.28556","title":"A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks","created":"2026-05-27","cited_by_count":0,"area":"agents"},{"id":"2607.19292","title":"The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.10030","title":"Causal Behavioral Evaluation of AI Agents at Scale via Automated Behavioral Science","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.11274","title":"Agent Safety Should Be a Runtime Contract","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2608.14940","title":"When Is an Agent Evaluation Over? Outcome Finality and Cross-Unit Separation","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.29463","title":"Benchmark Contamination: A Taxonomy Organized by Defeated Mitigation","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.04748","title":"Same Request, Different Answer: Quantization Amplifies Cache-Induced Divergence in LLM Serving","created":"2026-09-04","cited_by_count":0,"area":"inference"},{"id":"2609.17394","title":"Coding Agents Have Converged: Why the SWE-bench Leaderboard Can No Longer Order Its Top Entries, and What to Measure Instead","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.24516","title":"LLJ Cards: Best practices for the Use of LLMs as Judges","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.26826","title":"What Makes a Terminal-Bench Task Hard? Separating Genuine Hardness from Fake-Hardness on an Adjudicated Agentic Corpus","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.33023","title":"SRE-Marathon: A Continuous, Change-Driven Benchmark for Autonomous Site Reliability Agents","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33812","title":"Identical Runs, Different Results: Benchmarking AI Coding Agents on Open-Weight Models","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.35143","title":"Timeline-Bench: Evaluating Agents on Realistic Video-Editing Tasks, from Raw Footage to Final Cut","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.37236","title":"Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38469","title":"The Backdrop Exposes What the World Around an Agent Costs It","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.01618","title":"Agents Are Systems, Not Models: Rethinking Agentic Evaluation","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.02304","title":"SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02563","title":"OpenGameEval: Benchmarking Agentic Programming and Exploration in a Stateful Game Engine","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.03585","title":"Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.04123","title":"Agent Reliability Profiles in Financial Services","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04379","title":"AgentPersonaBench: Benchmarking Persona-Driven User Simulation","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.09142","title":"Finding Blind Spots in AppWorld and WorkArena Task Verifiers","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.09193","title":"Bookkeeping, Composition, or Unreachable Gold? Reading MemoryAgentBench's Conflict-Resolution Scores Against a Frozen Last-Write Resolver","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":"100"}