{"total":21,"rows":[{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2606.07297","title":"SWE-Explore: Benchmarking How Coding Agents Explore Repositories","created":"2026-06-05","cited_by_count":21,"area":"agents"},{"id":"2606.20683","title":"From Question Answering to Task Completion: A Survey on Agent System and Harness Design","created":"2026-06-14","cited_by_count":12,"area":"agents"},{"id":"2606.11864","title":"CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding","created":"2026-06-10","cited_by_count":7,"area":"agents"},{"id":"2609.20812","title":"Quantifying Overclaiming Propensity in Frontier LLM Agents","created":"2026-09-17","cited_by_count":4,"area":"agents"},{"id":"2606.02875","title":"Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks","created":"2026-06-01","cited_by_count":3,"area":"agents"},{"id":"2607.09691","title":"What Context Does a Coding Agent Actually Need to Act?","created":"2026-06-19","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":"2608.05141","title":"OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2606.08151","title":"Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents","created":"2026-06-06","cited_by_count":1,"area":"agents"},{"id":"2607.22807","title":"The Best Programming Language for Tokenmaxxing: An Investigation of Coding Agent Behavior Across Programming Languages","created":"2026-07-24","cited_by_count":1,"area":"agents"},{"id":"2608.16295","title":"Executable Code Knowledge: Code as a Native, Validation-Carrying Knowledge Representation for AI Coding Agents","created":"2026-08-17","cited_by_count":1,"area":"agents"},{"id":"2603.00601","title":"Theory of Code Space: Do Code Agents Understand Software Architecture?","created":"2026-02-28","cited_by_count":0,"area":"agents"},{"id":"2606.26346","title":"How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2607.25431","title":"CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents","created":"2026-07-28","cited_by_count":0,"area":"agents"},{"id":"2609.15939","title":"Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale","created":"2026-09-14","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":"2609.31587","title":"Compact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfer","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.36319","title":"StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.18004","title":"SWEPatchTest: Evaluating Software Tests Beyond Reproduction","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.20003","title":"What Coding Agents Leave Unsaid: Measuring Task-State Gaps Between Execution and Reports","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}