Definition
Tool use is the model’s ability to call external functions — a calculator, a search engine, a code interpreter, an API — and use the results in its response. It’s what turns a chat model into something that can actually act in the world.
Episodes covering this
Worth reading next
Papers we haven't done a deep dive on yet, but would recommend on this topic.
- Search-o1: Agentic Search-Enhanced Large Reasoning Models
- AgentDojo: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents
- Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- ToolBench: Facilitating Large Language Models to Master 16000+ Real-world APIs
- τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- AlphaProof and AlphaGeometry 2: AI achieves silver-medal standard solving International Mathematical Olympiad problems
- ReAct: Synergizing Reasoning and Acting in Language Models
- Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Model Parameters
- Toolformer: Language Models Can Teach Themselves to Use Tools
- Graph Neural Networks: A Review of Methods and Applications
- AppAgent: Multimodal Agents as Smartphone Users
- Code as Policies: Language Model Programs for Embodied Control
- Self-Refine: Iterative Refinement with Self-Feedback
- Reflexion: Language Agents with Verbal Reinforcement Learning
- ECHO: Environment-Conditioned Hierarchical Offline Reinforcement Learning
- From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces
- Voyager: An Open-Ended Embodied Agent with Large Language Models