{"total":17,"rows":[{"id":"2508.18993","title":"GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging","created":"2025-08-26","cited_by_count":25,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2512.04111","title":"CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding","created":"2025-11-30","cited_by_count":12,"area":"agents"},{"id":"2512.10398","title":"Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases","created":"2025-12-11","cited_by_count":11,"area":"agents"},{"id":"2602.04254","title":"Scaling Agentic Verifier for Competitive Coding","created":"2026-02-04","cited_by_count":7,"area":"agents"},{"id":"2606.21228","title":"Sakana Fugu Technical Report","created":"2026-06-19","cited_by_count":4,"area":"agents"},{"id":"2605.24693","title":"CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming","created":"2026-05-23","cited_by_count":3,"area":"agents"},{"id":"2603.15921","title":"VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?","created":"2026-03-16","cited_by_count":2,"area":"agents"},{"id":"2604.10182","title":"Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decision","created":"2026-04-11","cited_by_count":2,"area":"agents"},{"id":"2606.31182","title":"AI-Assisted Discovery of Convex Relaxations via Dual Agents","created":"2026-06-30","cited_by_count":2,"area":"agents"},{"id":"2608.01684","title":"GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks","created":"2026-08-03","cited_by_count":2,"area":"agents"},{"id":"2605.19782","title":"Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code Optimization","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2606.32007","title":"AxDafny: Agentic Verified Code Generation in Dafny","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2609.15983","title":"Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science","created":"2026-09-14","cited_by_count":1,"area":"agents"},{"id":"2510.27628","title":"Validity Is What You Need","created":"2025-10-31","cited_by_count":0,"area":"agents"},{"id":"2609.00058","title":"CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language","created":"2026-08-30","cited_by_count":0,"area":"agents"},{"id":"2610.19433","title":"EvoProbe: Evaluation-Driven Benchmark Evolution for LLM Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}