{"total":99,"rows":[{"id":"2512.13564","title":"Memory in the Age of AI Agents","created":"2025-12-15","cited_by_count":303,"area":"agents"},{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279,"area":null},{"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":"2504.07164","title":"R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents","created":"2025-04-09","cited_by_count":158,"area":"lr"},{"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":"2505.08638","title":"TRAIL: Trace Reasoning and Agentic Issue Localization","created":"2025-05-13","cited_by_count":104,"area":"lr"},{"id":"2506.18824","title":"Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories","created":"2025-06-23","cited_by_count":81,"area":"lr"},{"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":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"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":"2412.02883","title":"TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?","created":"2024-12-03","cited_by_count":34,"area":null},{"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":"2512.17419","title":"SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories","created":"2025-12-19","cited_by_count":28,"area":null},{"id":"2502.05368","title":"Otter: Generating Tests from Issues to Validate SWE Patches","created":"2025-02-07","cited_by_count":25,"area":null},{"id":"2505.23671","title":"GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents","created":"2025-05-29","cited_by_count":25,"area":"agents"},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2506.01372","title":"AI Scientists Fail Without Strong Implementation Capability","created":"2025-06-02","cited_by_count":21,"area":null},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19,"area":"agents"},{"id":"2602.02361","title":"SWE-Universe: Scale Real-World Verifiable Environments to Millions","created":"2026-02-02","cited_by_count":19,"area":null},{"id":"2607.13104","title":"Self-Improvements in Modern Agentic Systems: A Survey","created":"2026-07-14","cited_by_count":19,"area":"agents"},{"id":"2505.08253","title":"Evaluating LLM Metrics Through Real-World Capabilities","created":"2025-05-13","cited_by_count":18,"area":null},{"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":"2601.08778","title":"Pervasive Annotation Errors Break Text-to-SQL Benchmarks and Leaderboards","created":"2026-01-13","cited_by_count":13,"area":null},{"id":"2411.13323","title":"Are Large Language Models Memorizing Bug Benchmarks?","created":"2024-11-20","cited_by_count":12,"area":null},{"id":"2507.09108","title":"SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation","created":"2025-07-12","cited_by_count":12,"area":null},{"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":"2512.04329","title":"A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks","created":"2025-12-03","cited_by_count":11,"area":"rag"},{"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":"2507.11059","title":"SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks","created":"2025-07-15","cited_by_count":9,"area":null},{"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":"2506.10954","title":"SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks","created":"2025-06-12","cited_by_count":7,"area":null},{"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":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2606.28279","title":"Agentic Hardware Design as Repository-Level Code Evolution","created":"2026-06-26","cited_by_count":6,"area":"agents"},{"id":"2505.04670","title":"LLM Code Customization with Visual Results: A Benchmark on TikZ","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2505.23932","title":"SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2604.02648","title":"GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers","created":"2026-04-03","cited_by_count":5,"area":null},{"id":"2605.26321","title":"Anchor: Mitigating Artifact Drift in Agent Benchmark Generation","created":"2026-05-25","cited_by_count":5,"area":null},{"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":"2509.24091","title":"PerfBench: Can Agents Resolve Real-World Performance Bugs?","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2512.23328","title":"CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations","created":"2025-12-29","cited_by_count":3,"area":"lr"},{"id":"2602.04296","title":"ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenas","created":"2026-02-04","cited_by_count":3,"area":null},{"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":"2604.06111","title":"AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2606.00750","title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2606.17799","title":"Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering","created":"2026-06-16","cited_by_count":3,"area":"agents"},{"id":"2607.19843","title":"Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes","created":"2026-07-22","cited_by_count":3,"area":null},{"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":"2504.21276","title":"Assessing LLM code generation quality through path planning tasks","created":"2025-04-30","cited_by_count":2,"area":null},{"id":"2508.02473","title":"NES: An Instruction-Free, Low-Latency Next Edit Suggestion Framework Powered by Learned Historical Editing Trajectories","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2603.20380","title":"Herding CATs: ALARA for Agent Harness Engineering in Portable Composable Multi-Agent Teams","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2603.21454","title":"Cross-Context Verification: Hierarchical Detection of Benchmark Contamination through Session-Isolated Analysis","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2605.29277","title":"Code-QA-Bench: Separating Code Reasoning from Documentation Memorization in Repository-Level QA","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"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":"2607.02436","title":"Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study","created":"2026-07-02","cited_by_count":2,"area":"lr"},{"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":"2608.13566","title":"Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2602.18453","title":"LLM-Assisted Replication for Quantitative Social Science","created":"2026-02-04","cited_by_count":1,"area":null},{"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":"2607.28587","title":"PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2607.28887","title":"To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.06663","title":"The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents","created":"2026-08-07","cited_by_count":1,"area":"lr"},{"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":"2503.04784","title":"KunlunBaize: LLM with Multi-Scale Convolution and Multi-Token Prediction Under TransformerX Framework","created":"2025-02-27","cited_by_count":0,"area":null},{"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":"2604.27551","title":"Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis","created":"2026-04-30","cited_by_count":0,"area":null},{"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":"2606.05770","title":"Human Oversight and Overload: Two Hidden and Costly Burdens of AI-Assisted Software Engineering","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.25973","title":"Helpful or Harmful? Evaluating LLM-Assisted Vulnerability Patching via a Human Study","created":"2026-06-24","cited_by_count":0,"area":null},{"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":"2607.14049","title":"Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"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":"2609.29754","title":"SWE-PolyVision: Benchmarking Cross-Image Abductive Reasoning for Repository-Level Software Engineering","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"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}