Harrison Chase, the CEO and Founder of LangChain, gave a talk at Sequoia about the future of agents. Let’s watch (and discuss)!
1 Like
Thank you @PaulBellow, I just watched the first video and am in the midst of watching the second.
In the second video, in the chapter or segment on interesting projects (approximately 10m30s - 13m30s), proximate to some discussion about D&D and customer-support bots, Harrison Chase mentions state machines in the context of complex flow engineering.
On these topics, here is a related 2024 publication:
Wu, Yiran, Tianwei Yue, Shaokun Zhang, Chi Wang, and Qingyun Wu. “StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows.” arXiv preprint arXiv:2403.11322 (2024). [PDF]
It is a notable trend to use Large Language Models (LLMs) to tackle complex tasks, e.g., tasks that require a sequence of actions and dynamic interaction with tools and external environments. In this paper, we propose StateFlow, a novel LLM-based task-solving paradigm that conceptualizes complex task-solving processes as state machines. In StateFlow, we distinguish between “process grounding” (via state and state transitions) and “sub-task solving” (through actions within a state), enhancing control and interpretability of the task-solving procedure. A state represents the status of a running process. The transitions between states are controlled by heuristic rules or decisions made by the LLM, allowing for a dynamic and adaptive progression. Upon entering a state, a series of actions is executed, involving not only calling LLMs guided by different prompts, but also the utilization of external tools as needed. Our results show that StateFlow significantly enhances LLMs’ efficiency. For instance, StateFlow achieves 13% and 28% higher success rates compared to ReAct in InterCode SQL and ALFWorld benchmark, with 5× and 3× less cost respectively. We also show that StateFlow can be combined with iterative refining methods like Reflexion to further improve performance.
1 Like
Ooh, nice catch. Yeah, I imagine the AI DMs are about to get a lot better. I’ve got some ideas but no money or time.
Haven’t watched the entire interview yet, but wanted to share the overview and the full thing.