{"total":18,"rows":[{"id":"2601.16746","title":"SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents","created":"2026-01-23","cited_by_count":44,"area":"agents"},{"id":"2602.14878","title":"Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions","created":"2026-02-16","cited_by_count":17,"area":"agents"},{"id":"2512.04111","title":"CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding","created":"2025-11-30","cited_by_count":12,"area":"agents"},{"id":"2506.01839","title":"Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research","created":"2025-06-02","cited_by_count":10,"area":"agents"},{"id":"2504.13472","title":"CodeVisionary: An Agent-based Framework for Evaluating Large Language Models in Code Generation","created":"2025-04-18","cited_by_count":6,"area":"agents"},{"id":"2601.19510","title":"ALRM: Agentic LLM for Robotic Manipulation","created":"2026-01-27","cited_by_count":6,"area":"agents"},{"id":"2607.01456","title":"From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills","created":"2026-07-01","cited_by_count":6,"area":"agents"},{"id":"2510.10460","title":"Understanding and Bridging the Planner-Coder Gap: A Systematic Study on the Robustness of Multi-Agent Systems for Code Generation","created":"2025-10-12","cited_by_count":4,"area":"agents"},{"id":"2506.13171","title":"Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches","created":"2025-06-16","cited_by_count":3,"area":"agents"},{"id":"2603.09643","title":"MM-tau-p$^2$: Persona-Adaptive Prompting for Robust Multi-Modal Agent Evaluation in Dual-Control Settings","created":"2026-03-10","cited_by_count":3,"area":"agents"},{"id":"2607.00918","title":"From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"id":"2511.18528","title":"AutoLogger: A Multi-Agent Framework for the End-to-End Automated Logging","created":"2025-11-23","cited_by_count":1,"area":"agents"},{"id":"2607.03238","title":"An Empirical Study of Downstream Adaptation for Agent Skills","created":"2026-07-03","cited_by_count":1,"area":"agents"},{"id":"2606.06301","title":"More than a Judge: An Empirical Study of Agent-Human Interaction in Crowdsourced Testing Assessment","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2607.01808","title":"Archer: Towards Agentic Review for Compiler Optimizations","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2607.06713","title":"Reliable and Developer-Aligned Evaluation of Agents for Software Engineering","created":"2026-07-07","cited_by_count":0,"area":"agents"},{"id":"2609.30328","title":"When Is a Multi-Agent Code Judge Actually Grounded? Two Label-Free Measurements, and a Judge That Declines to Guess","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2610.06163","title":"Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair","created":"2026-10-05","cited_by_count":0,"area":"agents"}],"next_cursor":null}