2303.17071

It provides a simple, interpretable forum

Ref. 1A13-A

While many tasks can be formulated as a sin- gle prompt, later work has shown that breaking down single tasks into sub-tasks (called chain- ing) has benefits in terms of task performance and interpretability (Wu et al., 2022). Examples of chaining strategies include chain-of-thought (Wei et al., 2022) and other task-specific approaches (e.g, Agrawal et al. (2022)). Chain-of-thought strategies prompt the model to think through a problem as an expert might approach it, leading to improve- ments in some tasks (Liévin et al., 2022; Wang et al., 2022; Tafjord et al., 2022).

Ref. D1DD-B

We propose DERA: Dialog-Enabled Resolving

Ref. 2456-C

DERA is a general chat framework that leverages dialog-capable agents to iteratively work through a task (Figure 1). We focus on agent setups that work to probe knowledge sources, whether internal (from within GPT-4) or external (from text, documents, etc.). In approaches like chain-of-thought, these roles are generally performed jointly. In contrast, we propose that pairing an information-focused agent with a decision-maker agent will lead to a higher-quality output. Furthermore, this approach allows for DERA to alternate between processing knowledge and acting upon them, as opposed to doing them concurrently.

Ref. E030-D

First, we propose the use of a Researcher agent.

Ref. 0BC6-E