Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
98 tokens/sec
GPT-4o
61 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
8 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Navigating Complexity: Orchestrated Problem Solving with Multi-Agent LLMs (2402.16713v2)

Published 26 Feb 2024 in cs.MA

Abstract: LLMs have demonstrated remarkable capabilities in solving various tasks, yet they often struggle with comprehensively addressing complex and vague problems. Existing approaches, including multi-agent LLM systems, offer solutions to certain challenges but still require manual setup and lack scalability. To address this gap, we propose a novel approach leveraging decomposition to enable LLMs to tackle vague problems effectively. Our approach involves an orchestrating LLM that interacts with users to understand the problem and then decomposes it into tangible sub-problems. Instead of expecting the LLM to solve the entire problem in one go, we train it to ask follow-up questions to gain a deeper understanding of the user's requirements. Once the problem is adequately understood, the orchestrating LLM divides it into smaller, manageable sub-problems. Each sub-problem is then assigned to specialized LLM agents or non-LLM functions for resolution. These agents work in parallel to solve their respective sub-problems, with the orchestrating LLM overseeing the process and compiling the solutions into a comprehensive answer for the user. By adopting this decomposition approach, we alleviate the constraints imposed by token limitations on LLM outputs and empower them to provide nuanced solutions to complex and ambiguous problems. Through our approach, we aim to enable LLMs to think and operate more like humans, breaking down complex problems into manageable parts and collaboratively solving them. This not only enhances the problem-solving capabilities of LLMs but also offers a scalable and efficient method for addressing a wide range of real-world challenges.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. Large language models and the perils of their hallucinations. Critical Care, 27(1):1–2.
  2. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  3. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712.
  4. Chase, H. (2022). Langchain, october 2022. URL https://github. com/langchain-ai/langchain.
  5. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374.
  6. Can large language models be an alternative to human evaluations? arXiv preprint arXiv:2305.01937.
  7. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168.
  8. Lm vs lm: Detecting factual errors via cross examination. arXiv preprint arXiv:2305.13281.
  9. Cooperative ai: machines must learn to find common ground. Nature, 593(7857):33–36.
  10. Open problems in cooperative ai. arXiv preprint arXiv:2012.08630.
  11. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
  12. Improving factuality and reasoning in language models through multiagent debate. arXiv preprint arXiv:2305.14325.
  13. Human-like summarization evaluation with chatgpt. arXiv preprint arXiv:2304.02554.
  14. Emergent linguistic phenomena in multi-agent communication games.
  15. A real-world webagent with planning, long context understanding, and program synthesis. arXiv preprint arXiv:2307.12856.
  16. Negotiation and honesty in artificial intelligence methods for the board game of diplomacy. Nature Communications, 13(1):7214.
  17. Multi-agent communication meets natural language: Synergies between functional and structural language learning.
  18. Emergent translation in multi-agent communication.
  19. Camel: Communicative agents for" mind" exploration of large scale language model society. arXiv preprint arXiv:2303.17760.
  20. Encouraging divergent thinking in large language models through multi-agent debate. arXiv preprint arXiv:2305.19118.
  21. Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation. arXiv preprint arXiv:2305.01210.
  22. Gpteval: Nlg evaluation using gpt-4 with better human alignment. arXiv preprint arXiv:2303.16634.
  23. OpenAI (2023). Gpt-4 technical report. arxiv 2303.08774. View in Article, 2:13.
  24. Training language models to follow instructions with human feedback, 2022. URL https://arxiv. org/abs/2203.02155, 13.
  25. Gorilla: Large language model connected with massive apis. arXiv preprint arXiv:2305.15334.
  26. Communicative agents for software development. arXiv preprint arXiv:2307.07924.
  27. Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789.
  28. Rasal, S. (2024). Llm harmony: Multi-agent communication for problem solving. arXiv preprint arXiv:2401.01312.
  29. Multitask prompted training enables zero-shot task generalization. arXiv preprint arXiv:2110.08207.
  30. Self-critiquing models for assisting human evaluators. arXiv preprint arXiv:2206.05802.
  31. Are large language models good evaluators for abstractive summarization? arXiv preprint arXiv:2305.13091.
  32. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
  33. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682.
  34. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837.
  35. Large language models are diverse role-players for summarization evaluation. arXiv preprint arXiv:2303.15078.
  36. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629.
  37. Judging llm-as-a-judge with mt-bench and chatbot arena. arXiv preprint arXiv:2306.05685.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Sumedh Rasal (6 papers)
  2. E. J. Hauer (2 papers)