{"total":52,"rows":[{"id":"2602.15763","title":"GLM-5: from Vibe Coding to Agentic Engineering","created":"2026-02-17","cited_by_count":587,"area":"agents"},{"id":"2511.13646","title":"Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?","created":"2025-11-17","cited_by_count":95,"area":"agents"},{"id":"2508.11987","title":"FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction","created":"2025-08-16","cited_by_count":59,"area":"agents"},{"id":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59,"area":"agents"},{"id":"2510.21614","title":"Huxley-G\\\"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine","created":"2025-10-24","cited_by_count":53,"area":"agents"},{"id":"2509.23045","title":"Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents","created":"2025-09-27","cited_by_count":41,"area":"agents"},{"id":"2603.00718","title":"SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?","created":"2026-02-28","cited_by_count":30,"area":"agents"},{"id":"2509.21766","title":"UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios","created":"2025-09-26","cited_by_count":26,"area":"agents"},{"id":"2602.05892","title":"ContextBench: A Benchmark for Context Retrieval in Coding Agents","created":"2026-02-05","cited_by_count":25,"area":"agents"},{"id":"2602.09892","title":"Immersion in the GitHub Universe: Scaling Coding Agents to Mastery","created":"2026-02-10","cited_by_count":22,"area":"agents"},{"id":"2603.03194","title":"BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?","created":"2026-03-03","cited_by_count":22,"area":"agents"},{"id":"2606.29957","title":"SWE-Together: Evaluating Coding Agents in Interactive User Sessions","created":"2026-06-29","cited_by_count":18,"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":"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":"2512.12216","title":"Training Versatile Coding Agents in Synthetic Environments","created":"2025-12-13","cited_by_count":13,"area":"agents"},{"id":"2511.05459","title":"SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models","created":"2025-11-07","cited_by_count":11,"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":"2607.00053","title":"SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks","created":"2026-06-30","cited_by_count":11,"area":"agents"},{"id":"2510.07307","title":"MLE-Smith: Scaling MLE Tasks with Automated Multi-Agent Pipeline","created":"2025-10-08","cited_by_count":9,"area":"agents"},{"id":"2601.07526","title":"MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era","created":"2026-01-12","cited_by_count":9,"area":"agents"},{"id":"2608.04205","title":"MatrAIx: Simulating the World with 8.3 Billion Persona Agents","created":"2026-08-04","cited_by_count":7,"area":"agents"},{"id":"2511.11332","title":"UFO3: Weaving the Digital Agent Galaxy","created":"2025-11-14","cited_by_count":6,"area":"agents"},{"id":"2603.16011","title":"FormulaCode: Evaluating Agentic Optimization on Large Codebases","created":"2026-03-16","cited_by_count":6,"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":"2607.06065","title":"SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review","created":"2026-07-07","cited_by_count":5,"area":"agents"},{"id":"2607.06184","title":"What Resolve Rate Hides: Trajectory Structure Diagnostics for Coding Agents","created":"2026-07-07","cited_by_count":5,"area":"agents"},{"id":"2608.23564","title":"SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?","created":"2026-08-24","cited_by_count":5,"area":"agents"},{"id":"2608.11386","title":"The Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent Behavior","created":"2026-08-11","cited_by_count":3,"area":"agents"},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2608.19854","title":"Repo0: Design-Driven Zero-to-All Code Generation","created":"2026-08-20","cited_by_count":3,"area":"agents"},{"id":"2510.17928","title":"EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning","created":"2025-10-20","cited_by_count":1,"area":"agents"},{"id":"2604.07789","title":"ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents","created":"2026-04-09","cited_by_count":1,"area":"agents"},{"id":"2606.25514","title":"Unlocking Model Potentials Through Adaptive Multi-Agent Scaffolding for Efficient Issue Resolution","created":"2026-06-24","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":"2609.04167","title":"SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2605.04637","title":"SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies","created":"2026-05-06","cited_by_count":0,"area":"agents"},{"id":"2606.05570","title":"TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2608.20851","title":"BC-Bench: Evaluating Agentic Engineering in a Domain-Specific Language for ERP","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2608.23341","title":"DPIAgent: Divide, Protocol, Isolate for Agentic Reproduction Test Generation","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2608.27831","title":"RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.20050","title":"The Missing Complement: State-Conditioned Minimal Sufficient Evidence for Coding Agents","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.27891","title":"Schr\\\"odinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.29465","title":"SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.37864","title":"AgentBug-Smith: Automatically Reproducing Real-World Harness Bugs in Agentic Systems","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.00648","title":"Incident-Arena: Getting agents to the last nine of reliability","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.03153","title":"EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.04375","title":"Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents","created":"2026-10-03","cited_by_count":0,"area":"agents"},{"id":"2610.10619","title":"TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.12569","title":"SWE-Duel: Towards a Self-Scaling Arena for Coding Agents","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.12598","title":"Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents","created":"2026-10-08","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"}],"next_cursor":null}