{"total":18,"rows":[{"id":"2406.08747","title":"StreamBench: Towards Benchmarking Continuous Improvement of Language Agents","created":"2024-06-13","cited_by_count":47,"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":"2403.05307","title":"Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents","created":"2024-03-08","cited_by_count":17,"area":"agents"},{"id":"2505.05283","title":"Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents","created":"2025-05-08","cited_by_count":11,"area":"agents"},{"id":"2608.14380","title":"AgentRewind: Recoverable Execution for Long-Horizon LLM Agents","created":"2026-08-14","cited_by_count":7,"area":"agents"},{"id":"2510.12831","title":"MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training","created":"2025-10-12","cited_by_count":5,"area":"agents"},{"id":"2506.08800","title":"Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents","created":"2025-06-10","cited_by_count":4,"area":"agents"},{"id":"2509.11145","title":"Text2Mem: A Unified Memory Operation Language for Memory Operating System","created":"2025-09-14","cited_by_count":3,"area":"agents"},{"id":"2507.10281","title":"Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence","created":"2025-07-14","cited_by_count":2,"area":"agents"},{"id":"2605.06897","title":"MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes","created":"2026-05-07","cited_by_count":2,"area":"agents"},{"id":"2307.07255","title":"Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems","created":"2023-07-14","cited_by_count":1,"area":"agents"},{"id":"2601.02643","title":"AWARE-US: Preference-Aware Infeasibility Resolution in Tool-Calling Agents","created":"2026-01-06","cited_by_count":1,"area":"agents"},{"id":"2510.14162","title":"FinAI Data Assistant: LLM-based Financial Database Query Processing with the OpenAI Function Calling API","created":"2025-10-15","cited_by_count":0,"area":"agents"},{"id":"2511.11933","title":"InData: Towards Secure Multi-Step, Tool-Based Data Analysis","created":"2025-11-14","cited_by_count":0,"area":"agents"},{"id":"2606.19319","title":"Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2607.22642","title":"CRAFT: Learn the Schema, Execute the Plan","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2609.21341","title":"What Stops a Small Language Model From Driving a Database Agent","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2610.02739","title":"Beyond Correctness: Resolving Underspecification in Agentic Text-to-SQL","created":"2026-10-02","cited_by_count":0,"area":"agents"}],"next_cursor":null}