Passive Goal Creator

Summary: Passive goal creator analyses users’ articulated goals through the dialogue interface.

Context: When querying agents to address certain issues, users provide related context and explain the goals in prompts.

Problem: Users may lack expertise of interacting with agents, and the provided information can be ambiguous for goal achievement.

Forces:

  • Underspecification. Users may not be able to provide thorough context information and specify precise goals to agents.
  • Efficiency. Users expect quick responses from agents.

Solution: Fig. 1 illustrates a simple graphical representation of passive goal creator. A foundation model-based agent provides a dialogue interface where users can directly specify the context and problems, which are transferred to passive goal creator for goal determination. Meanwhile, the passive goal creator can also retrieve related information from memory, including the repository of artefacts being worked on, relevant tools used in recent tasks, conversation histories, and the positive and negative examples, which are appended to the user’s prompt for goal-seeking. The generated goals are sent to other components for further task decomposition and completion. In this case, the agent passively receives input from users and generates the strategies to refine and clarify users’ goals, as it only receives the context information directly provided by users. Please note that in multi-agent systems, an agent can send prompts by invoking the API of another agent to assign specific task, while the latter agent analyses the received information and determine the goal.

Figure 1. Passive goal creator.

Benefits:

  • Interactivity. Users or other agents can interact with an agent via a dialogue interface or related APIs.
  • Goal-seeking. The agent can analyse user-provided context and retrieve related information from memory, to identify and determine the objectives and create corresponding strategies.
  • Efficiency. Users can directly send prompts to the agent through the dialogue interface, which is intuitive and easy to use.

Drawbacks:

  • Reasoning uncertainty. Users may have assorted backgrounds and experiences. Unclear or ambiguous context information may intensify the reasoning uncertainties, especially considering there are no standard prompt requirements.

Known uses:

  • Liu et al. [1] designed an agent that can communicate with users and help refine research questions via a dialogue interface.
  • Kannan et al. [2] proposed an agent for users to decompose and allocate tasks to robots through a dialogue interface.
  • HuggingGPT. HuggingGPT can generate responses to address user requests via a chatbot. Users’ requests including complex intents can be interpreted as their intended goals.

Related patterns:

  • Proactive goal creator. Proactive goal creator can be regarded an alternative of passive goal creator enabling multimodal context injection.
  • Prompt/response optimiser. Passive goal creator can first handle users’ inputs and transfer the goals and relevant context information to prompt/response optimiser for prompt refinement.

References:

[1] Y. Liu, S. Chen, H. Chen, M. Yu, X. Ran, A. Mo, Y. Tang, and Y. Huang, “How ai processing delays foster creativity: Exploring research question co-creation with an llm-based agent,” arXiv preprint arXiv:2310.06155, 2023.

[2] S. S. Kannan, V. L. Venkatesh, and B.-C. Min, “Smart-llm: Smart multi-agent robot task planning using large language models,” arXiv preprint arXiv:2309.10062, 2023.