TaReD: Tool-Aware Recursive Decomposition for Long-Horizon Tasks
cs.AI
Submitted: 2026-10-08
Updated: 2026-10-08
Comments: 15 pages, 3 figures, 2 tables
Code: https://github.com/WeiXiang-Mao/TaReD
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning
- Decomposed Prompting: A Modular Approach for Solving Complex Tasks
- API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs
- WebGPT: Browser-assisted question-answering with human feedback
- SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding
- ART: Automatic multi-step reasoning and tool-use for large language models
- Gorilla: Large Language Model Connected with Massive APIs
- Measuring and Narrowing the Compositionality Gap in Language Models
- ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
- Toolformer: Language Models Can Teach Themselves to Use Tools
- PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents
- RestGPT: Connecting Large Language Models with Real-World RESTful APIs
- ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases
- AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
- Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
- ReAct: Synergizing Reasoning and Acting in Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems