{"total":94,"rows":[{"id":"2603.25723","title":"Natural-Language Agent Harnesses","created":"2026-03-26","cited_by_count":61,"area":null},{"id":"2509.23586","title":"Reducing Cost of LLM Agents with Trajectory Reduction","created":"2025-09-28","cited_by_count":48,"area":"agents"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2601.16746","title":"SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents","created":"2026-01-23","cited_by_count":44,"area":"agents"},{"id":"2512.22087","title":"Context as a Tool: Context Management for Long-Horizon SWE-Agents","created":"2025-12-26","cited_by_count":43,"area":"agents"},{"id":"2606.06324","title":"From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws","created":"2026-06-04","cited_by_count":29,"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":"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":"2607.09996","title":"Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?","created":"2026-07-10","cited_by_count":18,"area":"agents"},{"id":"2509.09853","title":"SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints","created":"2025-09-11","cited_by_count":17,"area":"agents"},{"id":"2601.07264","title":"The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents","created":"2026-01-12","cited_by_count":16,"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":"2602.07900","title":"Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents","created":"2026-02-08","cited_by_count":14,"area":"lr"},{"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":"2601.22129","title":"SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents","created":"2026-01-29","cited_by_count":12,"area":"lr"},{"id":"2511.05931","title":"Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement","created":"2025-11-08","cited_by_count":9,"area":null},{"id":"2602.06593","title":"AgentStepper: Interactive Debugging of Software Development Agents","created":"2026-02-06","cited_by_count":9,"area":"agents"},{"id":"2510.16786","title":"More with Less: An Empirical Study of Turn-Control Strategies for Efficient Coding Agents","created":"2025-10-19","cited_by_count":8,"area":"agents"},{"id":"2511.00872","title":"A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering Tasks","created":"2025-11-02","cited_by_count":7,"area":"agents"},{"id":"2511.16004","title":"InfCode: Adversarial Iterative Refinement of Tests and Patches for Reliable Software Issue Resolution","created":"2025-11-20","cited_by_count":7,"area":null},{"id":"2601.05777","title":"EET: Experience-Driven Early Termination for Cost-Efficient Software Engineering Agents","created":"2026-01-09","cited_by_count":7,"area":"agents"},{"id":"2602.01465","title":"Agyn: A Multi-Agent System for Team-Based Autonomous Software Engineering","created":"2026-02-01","cited_by_count":7,"area":"agents"},{"id":"2511.16858","title":"Investigating Test Overfitting on SWE-bench","created":"2025-11-20","cited_by_count":6,"area":null},{"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":"2601.19066","title":"Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair","created":"2026-01-27","cited_by_count":6,"area":"agents"},{"id":"2602.19594","title":"ISO-Bench: Can Coding Agents Optimize Real-World Inference Workloads?","created":"2026-02-23","cited_by_count":6,"area":"agents"},{"id":"2606.04874","title":"Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents","created":"2026-06-03","cited_by_count":6,"area":"agents"},{"id":"2509.25894","title":"Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities","created":"2025-09-30","cited_by_count":5,"area":"agents"},{"id":"2510.03217","title":"Abstain and Validate: A Dual-LLM Policy for Reducing Noise in Agentic Program Repair","created":"2025-10-03","cited_by_count":5,"area":"agents"},{"id":"2510.22775","title":"Scalable Supervision for Software Agents via Patch Reasoning","created":"2025-10-26","cited_by_count":5,"area":"lr"},{"id":"2601.18044","title":"RGFL: Reasoning Guided Fault Localization for Automated Program Repair Using Large Language Models","created":"2026-01-25","cited_by_count":5,"area":"lr"},{"id":"2602.10471","title":"TestExplora: Benchmarking LLMs for Proactive Bug Discovery via Repository-Level Test Generation","created":"2026-02-11","cited_by_count":5,"area":null},{"id":"2602.24287","title":"Do LLMs Benefit From Their Own Words?","created":"2026-02-27","cited_by_count":5,"area":null},{"id":"2607.00990","title":"SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests","created":"2026-07-01","cited_by_count":5,"area":"agents"},{"id":"2608.03222","title":"Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks","created":"2026-08-04","cited_by_count":5,"area":"agents"},{"id":"2511.07017","title":"Benchmarking LLMs for Fine-Grained Code Review with Enriched Context in Practice","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2512.22469","title":"GraphLocator: Graph-guided Causal Reasoning for Issue Localization","created":"2025-12-27","cited_by_count":4,"area":"lr"},{"id":"2603.13258","title":"Your Code Agent Can Grow Alongside You with Structured Memory","created":"2026-02-25","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":"2605.17526","title":"SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering","created":"2026-05-17","cited_by_count":4,"area":"agents"},{"id":"2607.02911","title":"CoACT: Action-Preserving Observation Compression for Coding Agents","created":"2026-07-03","cited_by_count":4,"area":"agents"},{"id":"2608.00808","title":"Turning Interaction History into Execution State: A Runtime Layer for Long-Horizon Coding Agents","created":"2026-08-01","cited_by_count":4,"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":"2511.16005","title":"InfCode-C++: Intent-Guided Semantic Retrieval and AST-Structured Search for C++ Issue Resolution","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2512.21332","title":"C2LLM Technical Report: A New Frontier in Code Retrieval via Adaptive Cross-Attention Pooling","created":"2025-12-24","cited_by_count":3,"area":null},{"id":"2601.23257","title":"From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2604.05481","title":"On the Role of Fault Localization Context for LLM-Based Program Repair","created":"2026-04-07","cited_by_count":3,"area":null},{"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":"2607.05174","title":"AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments","created":"2026-07-06","cited_by_count":3,"area":"agents"},{"id":"2607.19653","title":"PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2608.08950","title":"Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework","created":"2026-08-09","cited_by_count":3,"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":"2601.13933","title":"VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution","created":"2026-01-20","cited_by_count":2,"area":"agents"},{"id":"2602.05242","title":"EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2604.06231","title":"Automating Database-Native Function Code Synthesis with LLMs","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2604.14609","title":"El Agente Forjador: Task-Driven Agent Generation for Quantum Simulation","created":"2026-04-16","cited_by_count":2,"area":"agents"},{"id":"2607.18213","title":"SWE-Pruner Pro: The Coder LLM Already Knows What to Prune","created":"2026-07-20","cited_by_count":2,"area":"agents"},{"id":"2607.18859","title":"PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2608.04458","title":"Architectural Implications of Agentic AI Workflows","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2608.18933","title":"SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution","created":"2026-08-19","cited_by_count":2,"area":"agents"},{"id":"2510.16059","title":"SIADAFIX: issue description response for adaptive program repair","created":"2025-10-17","cited_by_count":1,"area":"lr"},{"id":"2510.26287","title":"Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search","created":"2025-10-30","cited_by_count":1,"area":"agents"},{"id":"2512.01396","title":"BackportBench: A Multilingual Benchmark for Automated Backporting of Patches","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2602.13723","title":"Compiling Large Multi-Modal Requirement Documents into Runnable Software Systems: From an Agentic Test-Driven Perspective","created":"2026-02-14","cited_by_count":1,"area":"agents"},{"id":"2603.11356","title":"Resolving Java Code Repository Issues with iSWE Agent","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2605.22526","title":"\"Refactoring Runaway\": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution","created":"2026-05-21","cited_by_count":1,"area":"agents"},{"id":"2606.14948","title":"Beyond Correctness: Enhancing Architectural Reasoning in Code LLMs via Scalable Labeling with Agentic Judgment","created":"2026-06-12","cited_by_count":1,"area":"lr"},{"id":"2607.09553","title":"Writing Bug Reports for Software Repair Agents: What Information Matters Most?","created":"2026-07-10","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":"2607.29658","title":"Reusing Past Repairs Through Hierarchical Trajectory Abstraction for Coding Agents","created":"2026-07-31","cited_by_count":1,"area":"agents"},{"id":"2608.03961","title":"Interpretable Adaptive Sampling for LLM Test-Time Scaling","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2609.08318","title":"AttnCompress: Dynamic Attention-Guided Trajectory Compression for Software Engineering Agents","created":"2026-09-08","cited_by_count":1,"area":"agents"},{"id":"2510.13248","title":"Automated Network Protocol Testing with LLM Agents","created":"2025-10-15","cited_by_count":0,"area":"agents"},{"id":"2512.20957","title":"One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents","created":"2025-12-24","cited_by_count":0,"area":"agents"},{"id":"2601.04526","title":"Advancing Language Models for Code-related Tasks","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2604.11270","title":"Evaluating LLM Agents on Automated Software Analysis Tasks","created":"2026-04-13","cited_by_count":0,"area":"agents"},{"id":"2605.00433","title":"Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning","created":"2026-05-01","cited_by_count":0,"area":null},{"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":"2606.20881","title":"When Do Intrinsic Rewards Work for Code Reasoning? A Comprehensive Study","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2607.00700","title":"LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.01929","title":"Beyond Textual Repository Exploration: Dual-Modal Structural Reasoning for Agentic Issue Resolution","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2607.02857","title":"MOSAIC: Knowledge-Guided CLI Command Composition Attack in LLM Coding Agents","created":"2026-07-03","cited_by_count":0,"area":"agents"},{"id":"2607.18161","title":"TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2607.26451","title":"ExplainBench: Evaluating Code Explanations from Agents","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"id":"2607.27167","title":"SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch","created":"2026-07-29","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":"2608.27969","title":"openJiuwen: Beyond Static Harnesses for Long-Horizon Coding Agents","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.00568","title":"WiseSpec: Requirements-Driven Agents for Code Generation","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.26779","title":"CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2609.38606","title":"SecureVibe: Making Vibe Coding More Secure","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.10242","title":"TestGRAD: Evolving Test Suites via Failure Pattern Momentum for SWE-Agent Ensemble","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11578","title":"Chronos Enables Code Agents to Reason over Software Evolution","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.13356","title":"SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent Trajectories","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}