{"total":40,"rows":[{"id":"2606.29537","title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","created":"2026-06-28","cited_by_count":40,"area":"agents"},{"id":"2608.01964","title":"LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks","created":"2026-08-03","cited_by_count":13,"area":"agents"},{"id":"2606.16613","title":"CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies","created":"2026-06-15","cited_by_count":8,"area":"agents"},{"id":"2606.26300","title":"The Verification Horizon: No Silver Bullet for Coding Agent Rewards","created":"2026-06-24","cited_by_count":8,"area":"agents"},{"id":"2608.14380","title":"AgentRewind: Recoverable Execution for Long-Horizon LLM Agents","created":"2026-08-14","cited_by_count":7,"area":"agents"},{"id":"2607.21217","title":"ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders","created":"2026-07-23","cited_by_count":6,"area":"agents"},{"id":"2607.02606","title":"ChainSWE: Benchmarking Coding Agents on Multi-Bug Software Maintenance","created":"2026-07-01","cited_by_count":4,"area":"agents"},{"id":"2609.01481","title":"Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement","created":"2026-09-01","cited_by_count":4,"area":"agents"},{"id":"2606.09730","title":"SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research","created":"2026-06-08","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":"2608.08311","title":"Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution","created":"2026-08-08","cited_by_count":3,"area":"agents"},{"id":"2607.01087","title":"Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"id":"2607.27146","title":"MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis","created":"2026-07-29","cited_by_count":2,"area":"agents"},{"id":"2609.04611","title":"$\\tau^\\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction","created":"2026-09-04","cited_by_count":2,"area":"agents"},{"id":"2609.22068","title":"CodeMidas: Scaling Agentic Coding RL Environments from Code Itself","created":"2026-09-18","cited_by_count":2,"area":"agents"},{"id":"2609.24967","title":"Emergent Collusion in Long-Horizon LLM Agent Interaction","created":"2026-09-21","cited_by_count":2,"area":"agents"},{"id":"2606.13763","title":"Do programming languages still matter to your AI coding agent teammate? Evidence at scale from chess engines","created":"2026-06-11","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":"2607.27409","title":"SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements","created":"2026-07-29","cited_by_count":1,"area":"agents"},{"id":"2608.11469","title":"The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark","created":"2026-08-11","cited_by_count":1,"area":"agents"},{"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":"2609.22000","title":"RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents","created":"2026-09-18","cited_by_count":1,"area":"agents"},{"id":"2609.26781","title":"Agensh: Scaling Organizational Intelligence to 1,024 Agents","created":"2026-09-22","cited_by_count":1,"area":"agents"},{"id":"2609.38147","title":"Thinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2605.27492","title":"Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems","created":"2026-05-26","cited_by_count":0,"area":"agents"},{"id":"2607.27167","title":"SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"id":"2609.18805","title":"ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.25018","title":"OSFoundry: Building and Evolving Operating Systems with Specification-Guided Agents","created":"2026-08-08","cited_by_count":0,"area":"agents"},{"id":"2609.25591","title":"Evaluating Coding Agents on Kernel Exploit Generation","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2609.26777","title":"SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving","created":"2026-09-22","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":"2609.32227","title":"OptiArena: Can LLMs Improve Executable Algorithms under Fixed Resource Budgets?","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.32965","title":"Relic: From Multi-Agent Collaboration to Persistent Organizational Capability","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.38335","title":"E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.39564","title":"A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.09944","title":"AgentTime: Can Agents Estimate and Control Their Own Runtime?","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.13166","title":"Scaling Agentic Data for Long-Horizon Terminal Intelligence","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.13395","title":"ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.19810","title":"ReproBAIT: Can coding agents build their own biological AI tools?","created":"2026-10-14","cited_by_count":0,"area":"agents"},{"id":"2610.20344","title":"Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}