{"total":67,"rows":[{"id":"2507.23370","title":"Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling","created":"2025-07-31","cited_by_count":94,"area":"lr"},{"id":"2506.06251","title":"DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation","created":"2025-06-06","cited_by_count":45,"area":null},{"id":"2601.16746","title":"SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents","created":"2026-01-23","cited_by_count":44,"area":"agents"},{"id":"2510.00446","title":"LongCodeZip: Compress Long Context for Code Language Models","created":"2025-10-01","cited_by_count":39,"area":null},{"id":"2509.14635","title":"SWE-QA: Can Language Models Answer Repository-level Code Questions?","created":"2025-09-18","cited_by_count":38,"area":null},{"id":"2506.09443","title":"LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge","created":"2025-06-11","cited_by_count":37,"area":"safety"},{"id":"2507.10535","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","created":"2025-07-14","cited_by_count":33,"area":null},{"id":"2509.21117","title":"TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them","created":"2025-09-25","cited_by_count":20,"area":null},{"id":"2505.16222","title":"Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation","created":"2025-05-22","cited_by_count":18,"area":null},{"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":"2505.11604","title":"Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation","created":"2025-05-16","cited_by_count":11,"area":null},{"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":"2508.10014","title":"PersonaEval: Are LLM Evaluators Human Enough to Judge Role-Play?","created":"2025-08-06","cited_by_count":9,"area":null},{"id":"2507.03772","title":"Skewed Score: A statistical framework to assess autograders","created":"2025-07-04","cited_by_count":7,"area":null},{"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":"2506.18403","title":"The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs","created":"2025-06-23","cited_by_count":5,"area":null},{"id":"2509.18076","title":"Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates","created":"2025-09-22","cited_by_count":4,"area":"lr"},{"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":"2604.16790","title":"Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering","created":"2026-04-18","cited_by_count":4,"area":null},{"id":"2607.12885","title":"LLM Judges Can Be Too Generous When There Is No Reference Answer","created":"2026-07-14","cited_by_count":4,"area":null},{"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":"2603.06976","title":"A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity","created":"2026-03-07","cited_by_count":3,"area":"rag"},{"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":"2603.17067","title":"Evaluating Ill-Defined Tasks in Large Language Models","created":"2026-03-17","cited_by_count":3,"area":null},{"id":"2603.26567","title":"Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering","created":"2026-03-27","cited_by_count":3,"area":null},{"id":"2506.16440","title":"Evaluating the Use of LLMs for Documentation to Code Traceability","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2512.07666","title":"Bridging Code Graphs and Large Language Models for Better Code Understanding","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2603.01335","title":"Provable and Practical In-Context Policy Optimization for Self-Improvement","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"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":"2506.19185","title":"Spiritual-LLM : Gita Inspired Mental Health Therapy In the Era of LLMs","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2510.17163","title":"TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2510.26193","title":"RCScore: Quantifying Response Consistency in Large Language Models","created":"2025-10-30","cited_by_count":1,"area":null},{"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":"2512.15979","title":"OLAF: Towards Robust LLM-Based Annotation Framework in Empirical Software Engineering","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2512.20159","title":"Benchmarking Code LLM-as-a-Judge via Constrained Perturbation and Calibration","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2603.24586","title":"Comparing Developer and LLM Biases in Code Evaluation","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2604.24525","title":"Understanding the Limits of Automated Evaluation for Code Review Bots in Practice","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2605.22975","title":"When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith Guidance","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.30810","title":"Towards Knowledge Alignment in Code LLMs: Contrastive Unlearning for Evolving APIs","created":"2026-06-29","cited_by_count":1,"area":"safety"},{"id":"2607.03238","title":"An Empirical Study of Downstream Adaptation for Agent Skills","created":"2026-07-03","cited_by_count":1,"area":"agents"},{"id":"2510.05644","title":"The African Languages Lab: A Collaborative Approach to Advancing Low-Resource African NLP","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.13839","title":"Meronymic Ontology Extraction via Large Language Models","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2510.15746","title":"LLMs Judge Themselves: A Game-Theoretic Framework for Human-Aligned Evaluation","created":"2025-10-17","cited_by_count":0,"area":"alignment"},{"id":"2512.04319","title":"MANTRA: a Framework for Multi-stage Adaptive Noise TReAtment During Training","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2512.04442","title":"TaskEval: Synthesised Evaluation for Foundation-Model Tasks","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2512.04728","title":"Measuring the Unspoken: A Disentanglement Model and Benchmark for Psychological Analysis in the Wild","created":"2025-12-04","cited_by_count":0,"area":"mllm"},{"id":"2602.11924","title":"Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.14400","title":"Extending Minimal Pairs with Ordinal Surprisal Curves and Entropy Across Applied Domains","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2603.28295","title":"Evaluating LLMs for Answering Student Questions in Introductory Programming Courses","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.00586","title":"More Human, More Efficient: Aligning Annotations with Quantized SLMs","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.23027","title":"A Systematic Approach for Large Language Models Debugging","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2604.26986","title":"BatteryPass-12K: The First Dataset for the Novel Digital Battery Passport Conformance Task","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.06136","title":"BUILD-AND-FIND: An Effort-Aware Protocol for Evaluating Agent-Managed Codebases","created":"2026-05-07","cited_by_count":0,"area":null},{"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":"2607.08691","title":"ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2608.04549","title":"EuroExec: Frontier Language Models Fall Short of Expert Judgment on European Executive Decision Tasks","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.07038","title":"Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.10046","title":"Detecting Soft Skills in ML Engineering Roles CVs","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.09428","title":"XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?","created":"2026-09-08","cited_by_count":0,"area":null},{"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":"2609.37669","title":"Retrieve, Reproduce, Reveal: Dissecting Retrieval-Augmented Software Vulnerability Detection","created":"2026-09-29","cited_by_count":0,"area":"rag"},{"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}