MARCO: Multi-Agent Real-time Chat Orchestration

Anubhav Shrimal, Stanley Kanagaraj, Kriti Biswas, Swarnalatha Raghuraman, Anish Nediyanchath, Yi Zhang, Promod Yenigalla


Abstract
Large language model advancements have enabled the development of multi-agent frameworks to tackle complex, real-world problems such as to automate workflows that require interactions with diverse tools, reasoning, and human collaboration. We present MARCO, a Multi-Agent Real-time Chat Orchestration framework for automating workflows using LLMs. MARCO addresses key challenges in utilizing LLMs for complex, multi-step task execution in a production environment. It incorporates robust guardrails to steer LLM behavior, validate outputs, and recover from errors that stem from inconsistent output formatting, function and parameter hallucination, and lack of domain knowledge. Through extensive experiments we demonstrate MARCO’s superior performance with 94.48% and 92.74% accuracy on task execution for Digital Restaurant Service Platform conversations and Retail conversations datasets respectively along with 44.91% improved latency and 33.71% cost reduction in a production setting. We also report effects of guardrails in performance gain along with comparisons of various LLM models, both open-source and proprietary. The modular and generic design of MARCO allows it to be adapted for automating workflows across domains and to execute complex tasks through multi-turn interactions.
Anthology ID:
2024.emnlp-industry.102
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track
Month:
November
Year:
2024
Address:
Miami, Florida, US
Editors:
Franck Dernoncourt, Daniel Preoţiuc-Pietro, Anastasia Shimorina
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1381–1392
Language:
URL:
https://aclanthology.org/2024.emnlp-industry.102
DOI:
Bibkey:
Cite (ACL):
Anubhav Shrimal, Stanley Kanagaraj, Kriti Biswas, Swarnalatha Raghuraman, Anish Nediyanchath, Yi Zhang, and Promod Yenigalla. 2024. MARCO: Multi-Agent Real-time Chat Orchestration. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1381–1392, Miami, Florida, US. Association for Computational Linguistics.
Cite (Informal):
MARCO: Multi-Agent Real-time Chat Orchestration (Shrimal et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-industry.102.pdf