{"total":21,"rows":[{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"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":"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":"2603.21489","title":"Effective Strategies for Asynchronous Software Engineering Agents","created":"2026-03-23","cited_by_count":16,"area":"agents"},{"id":"2607.09510","title":"Failure as a Process: An Anatomy of CLI Coding Agent Trajectories","created":"2026-07-10","cited_by_count":13,"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":"2606.11213","title":"Beyond Compaction: Structured Context Eviction for Long-Horizon Agents","created":"2026-05-01","cited_by_count":8,"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":"2606.01279","title":"ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment","created":"2026-05-31","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":"2608.28281","title":"LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering","created":"2026-08-28","cited_by_count":3,"area":"agents"},{"id":"2610.08101","title":"Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems","created":"2026-10-06","cited_by_count":2,"area":"agents"},{"id":"2604.12162","title":"AlphaEval: Evaluating Agents in Production","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"id":"2606.19613","title":"StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns","created":"2026-06-17","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":"2604.11535","title":"Problem Reductions at Scale: Agentic Integration of Computationally Hard Problems","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2608.08236","title":"LatticeMind: A Conflict-Aware Memory Primitive for Multi-Agent Systems","created":"2026-08-08","cited_by_count":0,"area":"agents"},{"id":"2609.05571","title":"Grounded Skill Synthesis from Code at Scale for Agentic Intelligence","created":"2026-09-04","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":"2610.13395","title":"ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.14146","title":"Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}