{"total":23,"rows":[{"id":"2504.08703","title":"SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents","created":"2025-04-11","cited_by_count":85,"area":"agents"},{"id":"2605.11086","title":"ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?","created":"2026-05-11","cited_by_count":29,"area":"agents"},{"id":"2512.03262","title":"Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks","created":"2025-12-02","cited_by_count":22,"area":"agents"},{"id":"2602.11988","title":"Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?","created":"2026-02-12","cited_by_count":20,"area":"agents"},{"id":"2512.04987","title":"Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction","created":"2025-12-04","cited_by_count":17,"area":"agents"},{"id":"2509.22097","title":"SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios","created":"2025-09-26","cited_by_count":13,"area":"agents"},{"id":"2510.17862","title":"When \"Correct\" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?","created":"2025-10-15","cited_by_count":3,"area":"agents"},{"id":"2605.03952","title":"MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents","created":"2026-05-05","cited_by_count":3,"area":"agents"},{"id":"2605.06445","title":"Constraint Decay: The Fragility of LLM Agents in Backend Code Generation","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2511.20709","title":"DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents","created":"2025-11-24","cited_by_count":1,"area":"agents"},{"id":"2605.08382","title":"SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2606.01815","title":"CRAB-Bench: Evaluating LLM Agents under Complex Task Dependencies and Human-aligned User Simulation","created":"2026-06-01","cited_by_count":1,"area":"agents"},{"id":"2606.13757","title":"SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents","created":"2026-06-11","cited_by_count":1,"area":"agents"},{"id":"2606.15762","title":"Snyk VulnBench JS 1.0: Can LLMs Find the Same Bugs Twice?","created":"2026-06-14","cited_by_count":1,"area":"agents"},{"id":"2608.21747","title":"Architecture as Capability Equalizer for Coding Agents","created":"2026-08-22","cited_by_count":1,"area":"agents"},{"id":"2606.25195","title":"SoK: AI Secure Code Generation: Progress, Pitfalls, and Paths Forward","created":"2026-06-23","cited_by_count":0,"area":"agents"},{"id":"2607.11042","title":"BackendForge: Benchmarking Agentic End-to-End Code Generation with Backend Services","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2608.25457","title":"MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration","created":"2026-08-26","cited_by_count":0,"area":"agents"},{"id":"2609.19391","title":"MAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic Outputs","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2610.00850","title":"AuraForge: Scaling Security Supervision for Training Coding Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.06163","title":"Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.14766","title":"Last Secure Code Benchmark: Is the Code You Vibe Secure?","created":"2026-10-10","cited_by_count":0,"area":"agents"},{"id":"2610.15150","title":"Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses","created":"2026-10-10","cited_by_count":0,"area":"agents"}],"next_cursor":null}