{"list":"other","total":78,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040},{"id":"2601.11868","title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","created":"2026-01-17","cited_by_count":585},{"id":"2603.28052","title":"Meta-Harness: End-to-End Optimization of Model Harnesses","created":"2026-03-30","cited_by_count":309},{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204},{"id":"2205.12255","title":"TALM: Tool Augmented Language Models","created":"2022-05-24","cited_by_count":197},{"id":"2510.11967","title":"Scaling Long-Horizon LLM Agent via Context-Folding","created":"2025-10-13","cited_by_count":148},{"id":"2508.16153","title":"Memento: Fine-tuning LLM Agents without Fine-tuning LLMs","created":"2025-08-22","cited_by_count":127},{"id":"2403.16971","title":"AIOS: LLM Agent Operating System","created":"2024-03-25","cited_by_count":97},{"id":"2505.11942","title":"LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners","created":"2025-05-17","cited_by_count":78},{"id":"2603.03329","title":"AutoHarness: improving LLM agents by automatically synthesizing a code harness","created":"2026-02-10","cited_by_count":76},{"id":"2604.08224","title":"Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering","created":"2026-04-09","cited_by_count":74},{"id":"2604.06132","title":"Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents","created":"2026-04-07","cited_by_count":64},{"id":"2601.16443","title":"Endless Terminals: Scaling RL Environments for Terminal Agents","created":"2026-01-23","cited_by_count":54},{"id":"2502.05352","title":"ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks","created":"2025-02-07","cited_by_count":51},{"id":"2602.21193","title":"On Data Engineering for Scaling LLM Terminal Capabilities","created":"2026-02-24","cited_by_count":43},{"id":"2505.24785","title":"EXP-Bench: Can AI Conduct AI Research Experiments?","created":"2025-05-30","cited_by_count":37},{"id":"2605.10912","title":"WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation","created":"2026-05-11","cited_by_count":37},{"id":"2508.03501","title":"Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning","created":"2025-08-05","cited_by_count":36},{"id":"2508.04482","title":"OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use","created":"2025-08-06","cited_by_count":35},{"id":"2503.23434","title":"Towards Trustworthy GUI Agents: A Survey","created":"2025-03-30","cited_by_count":34},{"id":"2510.24795","title":"A Survey on Efficient Vision-Language-Action Models","created":"2025-10-27","cited_by_count":34},{"id":"2502.16069","title":"Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents","created":"2025-02-22","cited_by_count":33},{"id":"2604.05172","title":"ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces","created":"2026-04-06","cited_by_count":33},{"id":"2606.23321","title":"Tmax: A simple recipe for terminal agents","created":"2026-06-22","cited_by_count":33},{"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},{"id":"2602.07274","title":"TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents","created":"2026-02-06","cited_by_count":29},{"id":"2512.04324","title":"DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle","created":"2025-12-03","cited_by_count":23},{"id":"2605.24517","title":"ECHO: Terminal Agents Learn World Models for Free","created":"2026-05-23","cited_by_count":19},{"id":"2608.05466","title":"Recursive Synthesis for Long-Horizon Terminal Tasks","created":"2026-08-05","cited_by_count":19},{"id":"2603.02277","title":"Quantifying Frontier LLM Capabilities for Container Sandbox Escape","created":"2026-03-01","cited_by_count":18},{"id":"2604.02947","title":"AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents","created":"2026-04-03","cited_by_count":18},{"id":"2502.00964","title":"ML-Dev-Bench: Comparative Analysis of AI Agents on ML development workflows","created":"2025-02-03","cited_by_count":17},{"id":"2512.15688","title":"BashArena: A Control Setting for Highly Privileged AI Agents","created":"2025-12-17","cited_by_count":17},{"id":"2601.09923","title":"CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents","created":"2026-01-14","cited_by_count":17},{"id":"2604.01438","title":"ClawSafety: \"Safe\" LLMs, Unsafe Agents","created":"2026-04-01","cited_by_count":17},{"id":"2505.16975","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","created":"2025-05-22","cited_by_count":16},{"id":"2508.00031","title":"Git Context Controller: Manage the Context of LLM-based Agents like Git","created":"2025-07-30","cited_by_count":15},{"id":"2604.19572","title":"A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression","created":"2026-04-21","cited_by_count":15},{"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},{"id":"2505.20945","title":"IRCopilot: Automated Incident Response with Large Language Models","created":"2025-05-27","cited_by_count":13},{"id":"2506.19724","title":"From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking","created":"2025-06-24","cited_by_count":12},{"id":"2604.10577","title":"The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents","created":"2026-04-12","cited_by_count":12},{"id":"2606.22883","title":"CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents","created":"2026-06-22","cited_by_count":12},{"id":"2607.10891","title":"SETA: Scaling Environments for Terminal Agents","created":"2026-07-12","cited_by_count":12},{"id":"2509.22256","title":"Secure and Efficient Access Control for Computer-Use Agents via Context Space","created":"2025-09-26","cited_by_count":11},{"id":"2605.22535","title":"TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks","created":"2026-05-21","cited_by_count":10},{"id":"2507.11059","title":"SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks","created":"2025-07-15","cited_by_count":9},{"id":"2602.03255","title":"LPS-Bench: Benchmarking Safety Awareness of Computer-Use Agents in Long-Horizon Planning under Benign and Adversarial Scenarios","created":"2026-02-03","cited_by_count":9},{"id":"2606.03461","title":"What Makes Interaction Trajectories Effective for Training Terminal Agents?","created":"2026-06-02","cited_by_count":9},{"id":"2606.28480","title":"TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents","created":"2026-06-26","cited_by_count":9},{"id":"2507.14897","title":"AgentFly: Extensible and Scalable Reinforcement Learning for LM Agents","created":"2025-07-20","cited_by_count":8},{"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},{"id":"2608.06352","title":"CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks","created":"2026-08-06","cited_by_count":8},{"id":"2506.10954","title":"SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks","created":"2025-06-12","cited_by_count":7},{"id":"2506.14682","title":"AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models","created":"2025-06-17","cited_by_count":7},{"id":"2510.11688","title":"PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities","created":"2025-10-13","cited_by_count":7},{"id":"2602.19547","title":"CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents","created":"2026-02-23","cited_by_count":5},{"id":"2604.06742","title":"Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios","created":"2026-04-08","cited_by_count":5},{"id":"2601.15141","title":"CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning","created":"2026-01-21","cited_by_count":4},{"id":"2601.20886","title":"IDE-Bench: Evaluating Large Language Models as IDE Agents on Real-World Software Engineering Tasks","created":"2026-01-28","cited_by_count":4},{"id":"2603.06358","title":"A Scalable Benchmark for Repository-Oriented Long-Horizon Conversational Context Management","created":"2026-03-06","cited_by_count":4},{"id":"2605.08717","title":"Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents","created":"2026-05-09","cited_by_count":4},{"id":"2605.11504","title":"CTFusion: A CTF-based Benchmark for LLM Agent Evaluation","created":"2026-05-12","cited_by_count":4},{"id":"2603.10664","title":"Terminal Is All You Need: Design Properties for Human-AI Agent Collaboration","created":"2026-03-11","cited_by_count":3},{"id":"2603.20311","title":"kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation","created":"2026-03-19","cited_by_count":3},{"id":"2603.22744","title":"LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks","created":"2026-03-24","cited_by_count":3},{"id":"2603.26137","title":"ATime-Consistent Benchmark for Repository-Level Software Engineering Evaluation","created":"2026-03-27","cited_by_count":3},{"id":"2604.05336","title":"TRACE: Capability-Targeted Agentic Training","created":"2026-04-07","cited_by_count":3},{"id":"2605.14133","title":"ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents","created":"2026-05-13","cited_by_count":3},{"id":"2603.21454","title":"Cross-Context Verification: Hierarchical Detection of Benchmark Contamination through Session-Isolated Analysis","created":"2026-03-23","cited_by_count":2},{"id":"2605.02584","title":"Beyond State Machines: Executing Network Procedures with Agentic Tool-Calling Sequences","created":"2026-05-04","cited_by_count":2},{"id":"2606.21140","title":"Matching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents","created":"2026-06-19","cited_by_count":2},{"id":"2604.24038","title":"AgentPulse: A Continuous Multi-Signal Framework for Evaluating AI Agents in Deployment","created":"2026-04-27","cited_by_count":1},{"id":"2605.19627","title":"How Helpful is LLM Assistance in Network Operations? A Case Study at a Large Demonstration Network","created":"2026-05-19","cited_by_count":1},{"id":"2607.10455","title":"ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm","created":"2026-07-11","cited_by_count":1},{"id":"2608.10366","title":"DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?","created":"2026-08-11","cited_by_count":1}],"next_cursor":null}