{"total":53,"rows":[{"id":"2512.13564","title":"Memory in the Age of AI Agents","created":"2025-12-15","cited_by_count":303,"area":"agents"},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2507.21046","title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","created":"2025-07-28","cited_by_count":170,"area":"agents"},{"id":"2505.20411","title":"SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents","created":"2025-05-26","cited_by_count":142,"area":"agents"},{"id":"2506.11791","title":"SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks","created":"2025-06-13","cited_by_count":75,"area":"agents"},{"id":"2505.03733","title":"WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch","created":"2025-05-06","cited_by_count":72,"area":"agents"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2506.09289","title":"UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench","created":"2025-06-10","cited_by_count":45,"area":"agents"},{"id":"2509.06216","title":"Agentic Software Engineering: Foundational Pillars and a Research Roadmap","created":"2025-09-07","cited_by_count":41,"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":"2505.23671","title":"GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents","created":"2025-05-29","cited_by_count":25,"area":"agents"},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19,"area":"agents"},{"id":"2607.13104","title":"Self-Improvements in Modern Agentic Systems: A Survey","created":"2026-07-14","cited_by_count":19,"area":"agents"},{"id":"2512.10218","title":"Does SWE-Bench-Verified Test Agent Ability or Model Memory?","created":"2025-12-11","cited_by_count":16,"area":"agents"},{"id":"2510.08996","title":"Saving SWE-Bench: A Benchmark Mutation Approach for Realistic Agent Evaluation","created":"2025-10-10","cited_by_count":15,"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":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"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":"2605.26079","title":"Automated Benchmark Auditing for AI Agents and Large Language Models","created":"2026-05-25","cited_by_count":12,"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":"2605.07769","title":"Coding Agents Don't Know When to Act","created":"2026-05-08","cited_by_count":7,"area":"agents"},{"id":"2606.13995","title":"Dialogue SWE-Bench: A Benchmark for Dialogue-Driven Coding Agents","created":"2026-06-12","cited_by_count":7,"area":"agents"},{"id":"2512.22256","title":"Agentic Software Issue Resolution with Large Language Models: A Survey","created":"2025-12-24","cited_by_count":6,"area":"agents"},{"id":"2601.11077","title":"ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development","created":"2026-01-16","cited_by_count":6,"area":"agents"},{"id":"2606.28279","title":"Agentic Hardware Design as Repository-Level Code Evolution","created":"2026-06-26","cited_by_count":6,"area":"agents"},{"id":"2510.26790","title":"Gistify! Codebase-Level Understanding via Runtime Execution","created":"2025-10-30","cited_by_count":4,"area":"agents"},{"id":"2602.02262","title":"OmniCode: A Benchmark for Evaluating Software Engineering Agents","created":"2026-02-02","cited_by_count":4,"area":"agents"},{"id":"2604.06861","title":"REAgent: Requirement-Driven LLM Agents for Software Issue Resolution","created":"2026-04-08","cited_by_count":4,"area":"agents"},{"id":"2605.21996","title":"From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents","created":"2026-05-21","cited_by_count":4,"area":"agents"},{"id":"2502.18465","title":"Empirical Research on Utilizing LLM-based Agents for Automated Bug Fixing via LangGraph","created":"2025-01-29","cited_by_count":3,"area":"agents"},{"id":"2509.22504","title":"Estimating the Empowerment of Language Model Agents","created":"2025-09-26","cited_by_count":3,"area":"agents"},{"id":"2603.29399","title":"ELT-Bench-Verified: Benchmark Quality Issues Underestimate AI Agent Capabilities","created":"2026-03-31","cited_by_count":3,"area":"agents"},{"id":"2606.17799","title":"Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering","created":"2026-06-16","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":"2606.22417","title":"Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent","created":"2026-06-21","cited_by_count":2,"area":"agents"},{"id":"2608.08413","title":"Tangent: An Empirical Study of Testing Practices for LLM-Based Agent Applications","created":"2026-08-09","cited_by_count":2,"area":"agents"},{"id":"2607.07593","title":"What Makes a Good Bug Report for an AI Agent?","created":"2026-07-08","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":"2609.34262","title":"Maintaining Benchmarks Against Increasingly Capable Agents: Detection and Remediation of Unearned Passes","created":"2026-09-28","cited_by_count":1,"area":"agents"},{"id":"2601.21649","title":"SWE-Spot: Building Small Repo-Experts with Repository-Centric Learning","created":"2026-01-29","cited_by_count":0,"area":"agents"},{"id":"2605.02244","title":"The Conversations Beneath the Code: Triadic Data for Long-Horizon Software Engineering Agents","created":"2026-05-04","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":"2607.06411","title":"RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications","created":"2026-07-07","cited_by_count":0,"area":"agents"},{"id":"2609.11987","title":"Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.17394","title":"Coding Agents Have Converged: Why the SWE-bench Leaderboard Can No Longer Order Its Top Entries, and What to Measure Instead","created":"2026-09-15","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":"2609.33875","title":"Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.36161","title":"From Dead Code and Static Requirements to Working Engines: Software Revival with Coding Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.06193","title":"Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents","created":"2026-10-05","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":"2610.14216","title":"Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.14460","title":"Re-executing Coding-Agent Evaluations: Unchanged Decisions and Unresolved Policy Risk","created":"2026-10-10","cited_by_count":0,"area":"agents"}],"next_cursor":null}