Towards large language model-based personal agents in the enterprise: Current trends and open problems
Submission Type: Regular Long Paper
Submission Track: Theme Track: Large Language Models and the Future of NLP
Submission Track 2: Dialogue and Interactive Systems
Keywords: Large language models, task-oriented, chatbots, multi-modal
TL;DR: Using large language models as the brains of autonomous agents (especially in enterprise settings) still has open research challenges that must be addressed.
Abstract: There is an emerging trend to use large language models (LLMs) to reason about complex goals and orchestrate a set of pluggable tools or APIs to accomplish a goal. This functionality could, among other use cases, be used to build personal assistants for knowledge workers. While there are impressive demos of LLMs being used as autonomous agents or for tool composition, these solutions are not ready mission-critical enterprise settings. For example, they are brittle to input changes, and can produce inconsistent results for the same inputs. These use cases have many open problems in an exciting area of NLP research, such as trust and explainability, consistency and reproducibility, adherence to guardrails and policies, best practices for composable tool design, and the need for new metrics and benchmarks. This vision paper illustrates some examples of LLM-based autonomous agents that reason and compose tools, highlights cases where they fail, surveys some of the recent efforts in this space, and lays out the research challenges to make these solutions viable for enterprises.
Submission Number: 4902
Loading