Hey AI, Can You Solve Complex Tasks by Talking to Agents?

ACL '22 Talk for paper: https://www.semanticscholar.org/paper/Hey-AI%2C-Can-You-Solve-Complex-Tasks-by-Talking-to-Khot-Richardson/dbeff5429ff0caa85f9e02621928e787e789ca2b

Training giant models from scratch for each complex task is resource- and data-inefficient. To help develop models that can leverage existing systems, we propose a new challenge: Learning to solve complex tasks by communicating with existing agents (or models) in natural language. We design a synthetic benchmark, CommaQA, with three complex reasoning tasks (explicit, implicit, numeric) designed to be solved by communicating with existing QA agents. For instance, using text and table QA agents …

agents ai hey