Language Agents with Karthik

Transitions

1. Transition first from rule based learning to statistical learning
2. Rise of semantic parsing: statistical models of parsing
3. Then, moving from semantic parsing to large models—putting decision making and language modeling into the same bubble

Importance of LLMs

• They are simply better at understanding language inputs
• They can generate structured information (i.e. not just human language, JSONs, etc.)
• They can perform natural language “reasoning”—not just generate

(and natural language generation, abv)

• 1+3 gives you chain of thought reasoning
• 1+2 gives CALM, SayCan, and other types of RL text parsing in order to do stuff with robotics
• all three gives ReAct

ReAct

See ReAct

Problem: agents are not robust at all

https://github.com/ryoungj/ToolEmu

Key Challenges

See History of Agents and Their Challenges