Mind the Prompt: Self-adaptive Generation of Task Plan Explanations via LLMs

• URL: http://arxiv.org/abs/2604.21092v1
• Date: Wed, 22 Apr 2026 21:22:21 GMT
• Title: Mind the Prompt: Self-adaptive Generation of Task Plan Explanations via LLMs
• Abstract summary: We introduce a proof-of-concept self-adaptive approach that formalises prompt engineering as a cognitive and probabilistic decision-making process.<n>We evaluate the adaptive explanation generation and their qualities, both quantitatively and qualitatively.<n>Our results demonstrate the feasibility of integrating human cognition and user profile's feedback into automated prompt synthesis.
• Score: 41.48741921431306
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Integrating Large Language Models (LLMs) into complex software systems enables the generation of human-understandable explanations of opaque AI processes, such as automated task planning. However, the quality and reliability of these explanations heavily depend on effective prompt engineering. The lack of a systematic understanding of how diverse stakeholder groups formulate and refine prompts hinders the development of tools that can automate this process. We introduce COMPASS (COgnitive Modelling for Prompt Automated SynthesiS), a proof-of-concept self-adaptive approach that formalises prompt engineering as a cognitive and probabilistic decision-making process. COMPASS models unobservable users' latent cognitive states, such as attention and comprehension, uncertainty, and observable interaction cues as a POMDP, whose synthesised policy enables adaptive generation of explanations and prompt refinements. We evaluate COMPASS using two diverse cyber-physical system case studies to assess the adaptive explanation generation and their qualities, both quantitatively and qualitatively. Our results demonstrate the feasibility of COMPASS integrating human cognition and user profile's feedback into automated prompt synthesis in complex task planning systems.

Related papers

• Steering LLMs via Scalable Interactive Oversight [74.12746881843044]
  Large Language Models increasingly automate complex, long-horizon tasks such as emphvibe coding, a supervision gap has emerged.<n>It presents a critical challenge in scalable oversight: enabling humans to responsibly steer AI systems on tasks that surpass their own ability to specify or verify.
  arXiv  Detail & Related papers  (2026-02-04T04:52:00Z)
• Fundamentals of Building Autonomous LLM Agents [64.39018305018904]
  This paper reviews the architecture and implementation methods of agents powered by large language models (LLMs)<n>The research aims to explore patterns to develop "agentic" LLMs that can automate complex tasks and bridge the performance gap with human capabilities.
  arXiv  Detail & Related papers  (2025-10-10T10:32:39Z)
• o-MEGA: Optimized Methods for Explanation Generation and Analysis [1.4113638641649384]
  textbftexttto-mega is a tool designed to automatically identify the most effective explainable AI methods.<n>We demonstrate improved transparency in automated fact-checking systems.
  arXiv  Detail & Related papers  (2025-09-30T21:08:36Z)
• AI Automatons: AI Systems Intended to Imitate Humans [54.19152688545896]
  There is a growing proliferation of AI systems designed to mimic people's behavior, work, abilities, likenesses, or humanness.<n>The research, design, deployment, and availability of such AI systems have prompted growing concerns about a wide range of possible legal, ethical, and other social impacts.
  arXiv  Detail & Related papers  (2025-03-04T03:55:38Z)
• Interactive Agents to Overcome Ambiguity in Software Engineering [61.40183840499932]
  AI agents are increasingly being deployed to automate tasks, often based on ambiguous and underspecified user instructions.<n>Making unwarranted assumptions and failing to ask clarifying questions can lead to suboptimal outcomes.<n>We study the ability of LLM agents to handle ambiguous instructions in interactive code generation settings by evaluating proprietary and open-weight models on their performance.
  arXiv  Detail & Related papers  (2025-02-18T17:12:26Z)
• From Feature Importance to Natural Language Explanations Using LLMs with RAG [4.204990010424084]
  We introduce traceable question-answering, leveraging an external knowledge repository to inform responses of Large Language Models (LLMs) This knowledge repository comprises contextual details regarding the model's output, containing high-level features, feature importance, and alternative probabilities. We integrate four key characteristics - social, causal, selective, and contrastive - drawn from social science research on human explanations into a single-shot prompt, guiding the response generation process.
  arXiv  Detail & Related papers  (2024-07-30T17:27:20Z)
• Synergising Human-like Responses and Machine Intelligence for Planning in Disaster Response [10.294618771570985]
  We propose an attention-based cognitive architecture inspired by Dual Process Theory (DPT) This framework integrates, in an online fashion, rapid yet (human-like) responses with the slow but optimized planning capabilities of machine intelligence.
  arXiv  Detail & Related papers  (2024-04-15T15:47:08Z)
• Concept-Guided LLM Agents for Human-AI Safety Codesign [6.603483691167379]
  Generative AI is increasingly important in software engineering, including safety engineering, where its use ensures that software does not cause harm to people. It is crucial to develop more advanced and sophisticated approaches that can effectively address the complexities and safety concerns of software systems. We present an efficient, hybrid strategy to leverage Large Language Models for safety analysis and Human-AI codesign.
  arXiv  Detail & Related papers  (2024-04-03T11:37:01Z)
• Automated Process Planning Based on a Semantic Capability Model and SMT [50.76251195257306]
  In research of manufacturing systems and autonomous robots, the term capability is used for a machine-interpretable specification of a system function. We present an approach that combines these two topics: starting from a semantic capability model, an AI planning problem is automatically generated.
  arXiv  Detail & Related papers  (2023-12-14T10:37:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.