{"total":14,"rows":[{"id":"2608.21833","title":"GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?","created":"2026-08-22","cited_by_count":8,"area":"agents"},{"id":"2608.22631","title":"Learning Generalizable Behaviors for Terminal Agents","created":"2026-08-23","cited_by_count":2,"area":"agents"},{"id":"2608.10319","title":"Do Personalized Skills Help Coding Agents? An Empirical Study of Developer Interaction Histories","created":"2026-08-10","cited_by_count":1,"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":"2609.32490","title":"RepoMAS: Solving Progressively Specified Tasks with Issue-Driven Multi-Agent Systems","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33295","title":"TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.38269","title":"Zero2Repo: Can Coding Agents Build Repositories from Scratch?","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2609.40118","title":"Persistent Context Graphs for Efficient Memory Compaction in LLM Agents","created":"2026-09-30","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":"2610.11559","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":"2610.13395","title":"ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.14216","title":"Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.16402","title":"EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications","created":"2026-10-12","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"}],"next_cursor":null}