{"total":29,"rows":[{"id":"2503.14499","title":"Measuring AI Ability to Complete Long Software Tasks","created":"2025-03-18","cited_by_count":156,"area":null},{"id":"2410.03439","title":"ToolGen: Unified Tool Retrieval and Calling via Generation","created":"2024-10-04","cited_by_count":74,"area":null},{"id":"2407.09886","title":"Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation","created":"2024-07-13","cited_by_count":27,"area":null},{"id":"2406.20015","title":"ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models","created":"2024-06-28","cited_by_count":25,"area":null},{"id":"2503.17354","title":"HCAST: Human-Calibrated Autonomy Software Tasks","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2506.04625","title":"Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning","created":"2025-06-05","cited_by_count":24,"area":null},{"id":"2604.06185","title":"Benchmarking LLM Tool-Use in the Wild","created":"2026-02-13","cited_by_count":17,"area":null},{"id":"2601.10355","title":"Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text","created":"2026-01-15","cited_by_count":13,"area":null},{"id":"2503.22673","title":"ActionStudio: A Lightweight Framework for Data and Training of Large Action Models","created":"2025-03-28","cited_by_count":6,"area":null},{"id":"2505.13851","title":"A Challenge to Build Neuro-Symbolic Video Agents","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2412.12839","title":"From An LLM Swarm To A PDDL-Empowered HIVE: Planning Self-Executed Instructions In A Multi-Modal Jungle","created":"2024-12-17","cited_by_count":4,"area":null},{"id":"2603.04403","title":"FinRetrieval: A Benchmark for Financial Data Retrieval by AI Agents","created":"2026-01-02","cited_by_count":4,"area":null},{"id":"2603.05578","title":"Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent","created":"2026-03-05","cited_by_count":4,"area":null},{"id":"2511.19957","title":"AppSelectBench: Application-Level Tool Selection Benchmark","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2409.15523","title":"SEAL: Suite for Evaluating API-use of LLMs","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2506.17538","title":"ConsumerBench: Benchmarking Generative AI Applications on End-User Devices","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2511.05811","title":"MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic Scaling","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2605.04097","title":"CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2507.15501","title":"ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2602.00397","title":"Fast Forward: Accelerating LLM Prefill with Predictive FFN Sparsity","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2603.13773","title":"LiveWeb-IE: A Benchmark For Online Web Information Extraction","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2605.02411","title":"FitText: Evolving Agent Tool Ecologies via Memetic Retrieval","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2606.26118","title":"The Open Source Economic Index of AI Adoption and Capability","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2607.28840","title":"Benchmarks Are Not Validation: A System-Level View of Financial LLM Applications","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.03403","title":"Towards Robust Tool Use in Agents via Experience-Driven Adaptive Guidance","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.29007","title":"When Does Action Credit Need Updating?","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.30293","title":"Cartograph: Federated Tool Discovery with Operator-Attested Retrieval for AI Agents","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.38095","title":"Probe-Space Preconditioning for Fast and Stable Zero-Order Training","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}