{"total":26,"rows":[{"id":"2603.24755","title":"SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks","created":"2026-03-25","cited_by_count":30,"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":"2604.00594","title":"Agent psychometrics: Task-level performance prediction in agentic coding benchmarks","created":"2026-04-01","cited_by_count":11,"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":"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":"2603.23448","title":"Code Review Agent Benchmark","created":"2026-03-24","cited_by_count":4,"area":"agents"},{"id":"2603.23638","title":"Can LLM Agents Be CFOs? Benchmarking Long-Horizon Resource Allocation in an Uncertain Enterprise Environment","created":"2026-03-24","cited_by_count":4,"area":"agents"},{"id":"2605.15846","title":"RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades","created":"2026-05-15","cited_by_count":4,"area":"agents"},{"id":"2608.26218","title":"Same Model, Different Harness: Different Coding-Agent Results","created":"2026-08-26","cited_by_count":4,"area":"agents"},{"id":"2607.00041","title":"ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis","created":"2026-06-29","cited_by_count":3,"area":"agents"},{"id":"2608.00267","title":"LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2607.26777","title":"CodeSpec: Dual Executable Specifications for Agentic Long-Horizon Feature Development","created":"2026-07-29","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":"2605.21347","title":"Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents","created":"2026-05-20","cited_by_count":1,"area":"agents"},{"id":"2605.26086","title":"Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World","created":"2026-05-25","cited_by_count":1,"area":"agents"},{"id":"2607.28591","title":"Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2608.04682","title":"Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports","created":"2026-08-05","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":"2609.37143","title":"LoLBench: Evaluating Coding Agents with Long-Horizon Proposals on Large Software Systems","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2609.39982","title":"Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2607.02684","title":"Can Coding Agents Implement Missed Compiler Optimizations? Evaluating LLM Agents on LLVM Peephole Optimizations","created":"2026-07-02","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":"2609.26777","title":"SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2610.06193","title":"Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.11559","title":"SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.17616","title":"StateHarness: Maintaining Evolving Project State for Long-Horizon Coding Agents","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}