{"total":35,"rows":[{"id":"2607.22368","title":"Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI","created":"2026-07-24","cited_by_count":6,"area":"agents"},{"id":"2608.09802","title":"SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring","created":"2026-08-10","cited_by_count":6,"area":"agents"},{"id":"2608.10875","title":"VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?","created":"2026-08-11","cited_by_count":3,"area":"agents"},{"id":"2607.13705","title":"AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities","created":"2026-07-15","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":"2609.04852","title":"KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2609.06780","title":"Shortcutting the Fix: Identifying and Categorizing Agentic Exploits in Software Engineering Benchmarks","created":"2026-09-06","cited_by_count":1,"area":"agents"},{"id":"2609.19607","title":"DeltaSelect: Affordable A/B Testing for Coding Agents","created":"2026-09-17","cited_by_count":1,"area":"agents"},{"id":"2609.32577","title":"Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL","created":"2026-09-26","cited_by_count":1,"area":"agents"},{"id":"2609.37143","title":"LoLBench: Evaluating Coding Agents with Long-Horizon Proposals on Large Software Systems","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2609.38349","title":"MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2607.14573","title":"Alipay-PIBench: A Realistic Payment Integration Benchmark for Coding Agents","created":"2026-07-16","cited_by_count":0,"area":"agents"},{"id":"2608.27831","title":"RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.05395","title":"Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.13463","title":"Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures","created":"2026-09-11","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":"2609.26121","title":"DTOC: Dynamic Tool Output Compression for Adaptive Context Management in AI Agents","created":"2026-08-06","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":"2609.33356","title":"Long-Horizon Analog Design Bench: Benchmarking Agents on Hours-Long Analog and Mixed-Signal Circuit Design Tasks","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.33987","title":"Opera: A Verbal Critic Framework for Long-horizon Coding Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34649","title":"Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses","created":"2026-09-28","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":"2609.38372","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":"2609.39507","title":"LIBERO-Agent: Evaluating General-Purpose Agents for Direct Embodied Manipulation","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.04838","title":"MemTrace: State-Consistent Memory for Long-Horizon Coding Agents","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.09633","title":"Coding-Agent Benchmarks Should Match Their Users' Task Flows","created":"2026-10-07","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":"2610.10478","title":"Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.10619","title":"TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.14405","title":"SPROUT: Scaling Agentic Reinforcement Learning for Long-Horizon Software Engineering","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.17757","title":"Instructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.18004","title":"SWEPatchTest: Evaluating Software Tests Beyond Reproduction","created":"2026-10-13","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}