{"total":115,"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":"2506.11763","title":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","created":"2025-06-13","cited_by_count":248,"area":"agents"},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2406.18518","title":"APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets","created":"2024-06-26","cited_by_count":198,"area":"agents"},{"id":"2604.25850","title":"Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses","created":"2026-04-28","cited_by_count":142,"area":"agents"},{"id":"2503.00096","title":"BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology","created":"2025-02-28","cited_by_count":89,"area":"agents"},{"id":"2603.15401","title":"SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?","created":"2026-03-16","cited_by_count":82,"area":"agents"},{"id":"2506.11791","title":"SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks","created":"2025-06-13","cited_by_count":75,"area":"agents"},{"id":"2505.03733","title":"WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch","created":"2025-05-06","cited_by_count":72,"area":"agents"},{"id":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59,"area":"agents"},{"id":"2502.13897","title":"DataSciBench: An LLM Agent Benchmark for Data Science","created":"2025-02-19","cited_by_count":57,"area":"agents"},{"id":"2502.11705","title":"LLM Agents Making Agent Tools","created":"2025-02-17","cited_by_count":48,"area":"agents"},{"id":"2503.01763","title":"Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models","created":"2025-03-03","cited_by_count":47,"area":"agents"},{"id":"2604.24594","title":"Skill Retrieval Augmentation for Agentic AI","created":"2026-04-27","cited_by_count":44,"area":"agents"},{"id":"2505.07473","title":"Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks","created":"2025-05-12","cited_by_count":40,"area":"agents"},{"id":"2602.10975","title":"FeatureBench: Benchmarking Agentic Coding for Complex Feature Development","created":"2026-02-11","cited_by_count":34,"area":"agents"},{"id":"2602.14337","title":"LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces","created":"2026-02-15","cited_by_count":34,"area":"agents"},{"id":"2605.23950","title":"Stop Comparing LLM Agents Without Disclosing the Harness","created":"2026-05-07","cited_by_count":34,"area":"agents"},{"id":"2604.05172","title":"ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces","created":"2026-04-06","cited_by_count":33,"area":"agents"},{"id":"2506.03610","title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","created":"2025-06-04","cited_by_count":31,"area":"agents"},{"id":"2505.18286","title":"Single-agent or Multi-agent Systems? Why Not Both?","created":"2025-05-23","cited_by_count":29,"area":"agents"},{"id":"2506.19290","title":"Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs","created":"2025-06-24","cited_by_count":26,"area":"agents"},{"id":"2411.03562","title":"Kolb-Based Experiential Learning for Generalist Agents with Human-Level Kaggle Data Science Performance","created":"2024-11-05","cited_by_count":25,"area":"agents"},{"id":"2505.23671","title":"GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents","created":"2025-05-29","cited_by_count":25,"area":"agents"},{"id":"2512.04388","title":"Learning to Orchestrate Agents in Natural Language with the Conductor","created":"2025-12-04","cited_by_count":23,"area":"agents"},{"id":"2603.03823","title":"SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration","created":"2026-03-04","cited_by_count":23,"area":"agents"},{"id":"2410.18792","title":"An LLM Agent for Automatic Geospatial Data Analysis","created":"2024-10-24","cited_by_count":21,"area":"agents"},{"id":"2506.07972","title":"HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization","created":"2025-06-09","cited_by_count":21,"area":"agents"},{"id":"2410.12468","title":"Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios","created":"2024-10-16","cited_by_count":18,"area":"agents"},{"id":"2412.03624","title":"How to Correctly do Semantic Backpropagation on Language-based Agentic Systems","created":"2024-12-04","cited_by_count":18,"area":"agents"},{"id":"2606.29957","title":"SWE-Together: Evaluating Coding Agents in Interactive User Sessions","created":"2026-06-29","cited_by_count":18,"area":"agents"},{"id":"2607.09996","title":"Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?","created":"2026-07-10","cited_by_count":18,"area":"agents"},{"id":"2605.09423","title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","created":"2026-05-10","cited_by_count":17,"area":"agents"},{"id":"2410.15048","title":"MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration","created":"2024-10-19","cited_by_count":16,"area":"agents"},{"id":"2511.13998","title":"LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering","created":"2025-11-17","cited_by_count":16,"area":"agents"},{"id":"2606.30560","title":"TraceLab: Characterizing Coding Agent Workloads for LLM Serving","created":"2026-06-29","cited_by_count":16,"area":"agents"},{"id":"2504.18565","title":"RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents","created":"2025-04-21","cited_by_count":15,"area":"agents"},{"id":"2510.01285","title":"LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science","created":"2025-09-30","cited_by_count":15,"area":"agents"},{"id":"2510.09721","title":"A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System","created":"2025-10-10","cited_by_count":15,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2512.12216","title":"Training Versatile Coding Agents in Synthetic Environments","created":"2025-12-13","cited_by_count":13,"area":"agents"},{"id":"2410.14735","title":"Agent Skill Acquisition for Large Language Models via CycleQD","created":"2024-10-16","cited_by_count":12,"area":"agents"},{"id":"2606.20683","title":"From Question Answering to Task Completion: A Survey on Agent System and Harness Design","created":"2026-06-14","cited_by_count":12,"area":"agents"},{"id":"2411.13768","title":"Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecture","created":"2024-11-21","cited_by_count":11,"area":"agents"},{"id":"2505.05283","title":"Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents","created":"2025-05-08","cited_by_count":11,"area":"agents"},{"id":"2507.11633","title":"General Modular Harness for LLM Agents in Multi-Turn Gaming Environments","created":"2025-07-15","cited_by_count":11,"area":"agents"},{"id":"2511.05459","title":"SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models","created":"2025-11-07","cited_by_count":11,"area":"agents"},{"id":"2607.00053","title":"SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks","created":"2026-06-30","cited_by_count":11,"area":"agents"},{"id":"2601.20789","title":"SERA: Soft-Verified Efficient Repository Agents","created":"2026-01-28","cited_by_count":10,"area":"agents"},{"id":"2606.22902","title":"Agent-as-a-Router: Agentic Model Routing for Coding Tasks","created":"2026-06-22","cited_by_count":10,"area":"agents"},{"id":"2505.19481","title":"Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs","created":"2025-05-26","cited_by_count":9,"area":"agents"},{"id":"2510.24358","title":"Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluation","created":"2025-10-28","cited_by_count":9,"area":"agents"},{"id":"2605.17734","title":"Harnessing LLM Agents with Skill Programs","created":"2026-05-18","cited_by_count":9,"area":"agents"},{"id":"2605.24110","title":"EvoCode-Bench: Evaluating Coding Agents in Multi-Turn Iterative Interactions","created":"2026-05-22","cited_by_count":9,"area":"agents"},{"id":"2504.04220","title":"AdaCoder: An Adaptive Planning and Multi-Agent Framework for Function-Level Code Generation","created":"2025-04-05","cited_by_count":8,"area":"agents"},{"id":"2508.05508","title":"Auto-Eval Judge: Towards a General Agentic Framework for Task Completion Evaluation","created":"2025-08-07","cited_by_count":8,"area":"agents"},{"id":"2603.00187","title":"ClarEval: A Benchmark for Evaluating Clarification Skills of Code Agents under Ambiguous Instructions","created":"2026-02-27","cited_by_count":8,"area":"agents"},{"id":"2605.14415","title":"SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades","created":"2026-05-14","cited_by_count":7,"area":"agents"},{"id":"2501.05255","title":"CallNavi, A Challenge and Empirical Study on LLM Function Calling and Routing","created":"2025-01-09","cited_by_count":6,"area":"agents"},{"id":"2502.07487","title":"Multi-Agent Collaboration for Multilingual Code Instruction Tuning","created":"2025-02-11","cited_by_count":6,"area":"agents"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2603.00822","title":"ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Files","created":"2026-02-28","cited_by_count":6,"area":"agents"},{"id":"2603.16733","title":"IQuest-Coder-V1 Technical Report","created":"2026-03-17","cited_by_count":6,"area":"agents"},{"id":"2605.14460","title":"Exploiting LLM Agent Supply Chains via Payload-less Skills","created":"2026-05-14","cited_by_count":6,"area":"agents"},{"id":"2605.15377","title":"Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute","created":"2026-05-14","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":"2509.14477","title":"Ticket-Bench: A Kickoff for Multilingual and Regionalized Agent Evaluation","created":"2025-09-17","cited_by_count":5,"area":"agents"},{"id":"2510.23010","title":"TALM: Dynamic Tree-Structured Multi-Agent Framework with Long-Term Memory for Scalable Code Generation","created":"2025-10-27","cited_by_count":5,"area":"agents"},{"id":"2602.08222","title":"Weak-Driven Learning: How Weak Agents make Strong Agents Stronger","created":"2026-02-09","cited_by_count":5,"area":"agents"},{"id":"2510.14700","title":"LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?","created":"2025-10-16","cited_by_count":4,"area":"agents"},{"id":"2604.00835","title":"Agentic Tool Use in Large Language Models","created":"2026-04-01","cited_by_count":4,"area":"agents"},{"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":"2510.17925","title":"SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion","created":"2025-10-20","cited_by_count":3,"area":"agents"},{"id":"2603.06007","title":"MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing","created":"2026-03-06","cited_by_count":3,"area":"agents"},{"id":"2603.19583","title":"Skilled AI Agents for Embedded and IoT Systems Development","created":"2026-03-20","cited_by_count":3,"area":"agents"},{"id":"2606.07379","title":"Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests","created":"2026-06-05","cited_by_count":3,"area":"agents"},{"id":"2606.17799","title":"Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering","created":"2026-06-16","cited_by_count":3,"area":"agents"},{"id":"2607.19338","title":"CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents","created":"2026-07-21","cited_by_count":3,"area":"agents"},{"id":"2608.02499","title":"SWE-Touch: Benchmarking Coding Agents When Users Touch the Code","created":"2026-08-03","cited_by_count":3,"area":"agents"},{"id":"2608.25776","title":"EVOMAL: Self-Poisoning in Self-Evolving Coding Agents","created":"2026-08-26","cited_by_count":3,"area":"agents"},{"id":"2507.09481","title":"Evaluating LLMs on Sequential API Call Through Automated Test Generation","created":"2025-07-13","cited_by_count":2,"area":"agents"},{"id":"2511.09794","title":"Evaluating Software Process Models for Multi-Agent Class-Level Code Generation","created":"2025-11-12","cited_by_count":2,"area":"agents"},{"id":"2604.10182","title":"Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decision","created":"2026-04-11","cited_by_count":2,"area":"agents"},{"id":"2605.17439","title":"DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"id":"2605.27489","title":"HARP: Measuring Harm Amplification in Multi-Agent LLM Systems","created":"2026-05-26","cited_by_count":2,"area":"agents"},{"id":"2606.22678","title":"RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents","created":"2026-06-21","cited_by_count":2,"area":"agents"},{"id":"2608.00355","title":"CurveShift: Is Agent Progress Scalar? Separating Level from Shape","created":"2026-07-31","cited_by_count":2,"area":"agents"},{"id":"2608.19993","title":"Optimal Skill Selection for LLM Agents with Provable Bicriteria Guarantees","created":"2026-08-20","cited_by_count":2,"area":"agents"},{"id":"2608.23867","title":"Markets, Not Planners: Decentralized Orchestration of LLM Agents with Private Information","created":"2026-08-24","cited_by_count":2,"area":"agents"},{"id":"2609.26863","title":"SkillApt: Learning When to Activate Agent Skills from Counterfactual Evidence","created":"2026-09-22","cited_by_count":2,"area":"agents"},{"id":"2411.08432","title":"One STEP at a time: Language Agents are Stepwise Planners","created":"2024-11-13","cited_by_count":1,"area":"agents"},{"id":"2603.13384","title":"VulnAgent-R2: Evidence-Calibrated Multi-Agent Auditing for Repository-Level Vulnerability Detection","created":"2026-03-11","cited_by_count":1,"area":"agents"},{"id":"2605.27605","title":"Laguna M.1/XS.2 Technical Report","created":"2026-05-26","cited_by_count":1,"area":"agents"},{"id":"2607.27409","title":"SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2608.15008","title":"Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents","created":"2026-08-15","cited_by_count":1,"area":"agents"},{"id":"2605.14141","title":"Distribution-Aware Algorithm Design with LLM Agents","created":"2026-05-13","cited_by_count":0,"area":"agents"},{"id":"2607.05659","title":"Agents with Feelings? Personality and Emotion in Multi-Agent Software Teams","created":"2026-07-06","cited_by_count":0,"area":"agents"},{"id":"2607.07744","title":"PERFOPT-Bench: Evaluating Coding Agents on Software Performance Optimization","created":"2026-07-08","cited_by_count":0,"area":"agents"},{"id":"2607.10789","title":"Imaging-101: Benchmarking LLM Coding Agents on Scientific Computational Imaging","created":"2026-07-12","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}