Multi-Path Plan Generator

Summary: Multi-path plan generator allows for creating multiple choices at each intermediate step leading to achieving users’ goals.

Context: A agent is considered “black box” to users, while users may care about the process of how an agent achieve users’ goals.

Problem: How can an agent generate a high-quality, coherent, and efficient solution considering inclusiveness and diversity when presented with a complex task or problem?

Forces:

  • Underspecification. Users may assign tasks with high-level abstraction, which may be challenging for agents to handle the uncertainty or ambiguity in the provided context.
  • Coherence. Users and other interacting tools/agents will expect coherent responses or guidelines for achieving certain goals.
  • Alignment to human preference. Certain goals require agents to capture users’ preferences, to provide customised solutions.
  • Oversimplification. For particular complex tasks, agents may oversimplify the reasoning process, hence the provided solutions cannot satisfy users’ requirements.

Solution: Fig. 1 illustrates a high-level graphical representation of multi-path plan generator. Based on single-path plan generator, multi-path plan generator can create multiple choices at each step towards the achievement of goals. Users’ preferences may influence the subsequent intermediate steps, leading to different eventual plans. The employment of involved agents and tools will be adjusted accordingly. Tree-of-Thoughts [1] exemplifies this design pattern.

Figure 1. Multi-path plan generator.

Benefits:

  • Reasoning certainty. Multi-path plan generator can generate a plan with multiple choices of intermediate steps to resolve the uncertainty or ambiguity within reasoning process.
  • Coherence. The interacting users, agents and tools are provided a clear and coherent path towards the ultimate goals.
  • Alignment to human preference. Users can confirm each intermediate step to finalise the planning, hence human preferences are absorbed in the generated customised strategy.
  • Inclusiveness. The agent can specify multiple directions in the reasoning process for complex tasks.

Drawbacks:

  • Overhead. Task decomposition and multi-plan generation may increase the communication overhead between the user and agent.

Known uses:

  • AutoGPT. AutoGPT can make informed decisions by incorporating Tree-of-Thoughts as the multi-path plan generator.
  • Gemini. For a task, Gemini can generate multiple choices for users to decide. Upon receiving users’ responses, Gemini will provide multiple choices for the next step.
  • Open AI. GPT-4 was leveraged to implement a multi-path plan generator based on Tree-of-Thoughts.

Related patterns:

  • Incremental model querying. The agent can capture users’ preferences at each step and generate multi-path plans by iteratively querying the foundation model.
  • Single-path plan generator. Multi-path plan generator can be regarded an alternative of single-path plan generator for customised strategy.
  • Human-reflection. Multi-plan generator creates plans with various directions, and human-reflection can help finalise the plan with user feedback to determine the choice of each intermediate step.

References:

[1] S. Yao, D. Yu, J. Zhao, I. Shafran, T. Griffiths, Y. Cao, and K. Narasimhan, “Tree of thoughts: Deliberate problem solving with large language models,” Advances in Neural Information Processing Systems, vol. 36, 2024.