{"total":61,"rows":[{"id":"2503.13657","title":"Why Do Multi-Agent LLM Systems Fail?","created":"2025-03-17","cited_by_count":604,"area":"agents"},{"id":"2501.04227","title":"Agent Laboratory: Using LLM Agents as Research Assistants","created":"2025-01-08","cited_by_count":425,"area":"agents"},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2502.08235","title":"The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks","created":"2025-02-12","cited_by_count":152,"area":"lr"},{"id":"2505.23885","title":"OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation","created":"2025-05-29","cited_by_count":131,"area":"lr"},{"id":"2503.18102","title":"AgentRxiv: Towards Collaborative Autonomous Research","created":"2025-03-23","cited_by_count":72,"area":null},{"id":"2512.18470","title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","created":"2025-12-20","cited_by_count":59,"area":"agents"},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2502.00350","title":"OrcaLoca: An LLM Agent Framework for Software Issue Localization","created":"2025-02-01","cited_by_count":45,"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":"2502.05664","title":"CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging","created":"2025-02-08","cited_by_count":32,"area":"agents"},{"id":"2508.02744","title":"Large Language Model-based Data Science Agent: A Survey","created":"2025-08-02","cited_by_count":23,"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":"2410.01999","title":"CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding & Reasoning Capabilities of CodeLLMs","created":"2024-10-02","cited_by_count":18,"area":"lr"},{"id":"2603.05344","title":"Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned","created":"2026-03-05","cited_by_count":18,"area":"agents"},{"id":"2607.10487","title":"Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents","created":"2026-07-11","cited_by_count":18,"area":"agents"},{"id":"2602.09185","title":"AIDev: Studying AI Coding Agents on GitHub","created":"2026-02-09","cited_by_count":17,"area":"agents"},{"id":"2511.17198","title":"Designing Domain-Specific Agents via Hierarchical Task Abstraction Mechanism","created":"2025-11-21","cited_by_count":16,"area":"agents"},{"id":"2506.03828","title":"AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance","created":"2025-06-04","cited_by_count":15,"area":"agents"},{"id":"2603.20432","title":"Coding Agents are Effective Long-Context Processors","created":"2026-03-20","cited_by_count":12,"area":"agents"},{"id":"2605.13625","title":"How to Interpret Agent Behavior","created":"2026-05-13","cited_by_count":10,"area":null},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2512.23631","title":"BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimization","created":"2025-12-29","cited_by_count":7,"area":"lr"},{"id":"2509.14483","title":"An LLM-based multi-agent framework for agile effort estimation","created":"2025-09-17","cited_by_count":6,"area":"agents"},{"id":"2510.11004","title":"Automating Structural Engineering Workflows with Large Language Model Agents","created":"2025-10-13","cited_by_count":6,"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":"2604.26275","title":"Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineering","created":"2026-04-29","cited_by_count":6,"area":"lr"},{"id":"2505.12501","title":"ALAS: A Stateful Multi-LLM Agent Framework for Disruption-Aware Planning","created":"2025-05-18","cited_by_count":5,"area":"agents"},{"id":"2508.08322","title":"Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code","created":"2025-08-09","cited_by_count":5,"area":"agents"},{"id":"2606.14066","title":"FastContext: Training Efficient Repository Explorer for Coding Agents","created":"2026-06-12","cited_by_count":5,"area":"agents"},{"id":"2409.10372","title":"Integrated Design and Governance of Agentic AI Systems through Adaptive Information Modulation","created":"2024-09-16","cited_by_count":4,"area":"agents"},{"id":"2506.13932","title":"Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2603.01327","title":"SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution","created":"2026-03-01","cited_by_count":4,"area":"agents"},{"id":"2410.23402","title":"VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning","created":"2024-10-30","cited_by_count":3,"area":"lr"},{"id":"2506.03546","title":"From Virtual Agents to Robot Teams: A Multi-Robot Framework Evaluation in High-Stakes Healthcare Context","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2604.26102","title":"SWE-Edit: Rethinking Code Editing for Efficient SWE-Agent","created":"2026-04-28","cited_by_count":3,"area":"lr"},{"id":"2605.06717","title":"Agentic Coding Needs Proactivity, Not Just Autonomy","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2605.08647","title":"AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators","created":"2026-05-09","cited_by_count":3,"area":"agents"},{"id":"2608.24271","title":"Observability and Fault Injection for LLM-Based Multi-Agent Systems in Software Engineering","created":"2026-08-25","cited_by_count":3,"area":"agents"},{"id":"2603.26458","title":"Can AI Models Direct Each Other? Organizational Structure as a Probe into Training Limitations","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2603.27296","title":"A Multi-agent AI System for Deep Learning Model Migration from TensorFlow to JAX","created":"2026-03-28","cited_by_count":2,"area":null},{"id":"2502.08756","title":"From PowerPoint UI Sketches to Web-Based Applications: Pattern-Driven Code Generation for GIS Dashboard Development Using Knowledge-Augmented LLMs, Context-Aware Visual Prompting, and the React Framework","created":"2025-02-12","cited_by_count":1,"area":null},{"id":"2510.27630","title":"Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training","created":"2025-10-31","cited_by_count":1,"area":"agents"},{"id":"2601.11327","title":"Can Small Agents Collaborate to Beat a Single Large Language Model?","created":"2026-01-16","cited_by_count":1,"area":"agents"},{"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":"2605.14563","title":"Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation","created":"2026-05-14","cited_by_count":1,"area":"agents"},{"id":"2606.25514","title":"Unlocking Model Potentials Through Adaptive Multi-Agent Scaffolding for Efficient Issue Resolution","created":"2026-06-24","cited_by_count":1,"area":"agents"},{"id":"2607.29055","title":"Autonomous Repair for Multi-Agent Systems via Monte-Carlo Tree Search","created":"2026-07-31","cited_by_count":1,"area":"agents"},{"id":"2608.20485","title":"Terminal Agents: A Survey of AI Agents in Command-Line Environments","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2511.20656","title":"Context-Aware Visual Prompting: Automating Geospatial Web Dashboards with Large Language Models and Agent Self-Validation for Decision Support","created":"2025-10-10","cited_by_count":0,"area":"agents"},{"id":"2604.02578","title":"High Volatility and Action Bias Distinguish LLMs from Humans in Group Coordination","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.23088","title":"Code Broker: A Multi-Agent System for Automated Code Quality Assessment","created":"2026-04-25","cited_by_count":0,"area":"agents"},{"id":"2605.27787","title":"Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.11976","title":"Exploration Structure in LLM Agents for Multi-File Change Localization","created":"2026-06-10","cited_by_count":0,"area":"agents"},{"id":"2608.05521","title":"Reasoning from Traces: Divergence-Guided Agentic Repair of WebAssembly Discrepancies","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2609.04898","title":"RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.33822","title":"Vestrum: Improving Agent Harnesses by Adapting Their Verification, Structure and Memory","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"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":"2610.01108","title":"AgSpec: Pushing the Limits of Retrieval-Based Speculative Decoding in Coding Agent Pipelines","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.11600","title":"Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems","created":"2026-10-08","cited_by_count":0,"area":"agents"}],"next_cursor":null}