mlsanityData to 7 Oct 2026

Towards Conversational Development Environments: Using Theory-of-Mind and Multi-Agent Architectures for Requirements Refinement

arXiv 2505.20973 ↗First posted 27 May 2025cs.SE cs.AIcited by 1

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Foundation Models (FMs) have shown remarkable capabilities in various natural language tasks. However, their ability to accurately capture stakeholder requirements remains a significant challenge for using FMs for software development. This paper introduces a novel approach that leverages an FM-powered multi-agent system called AlignMind to address this issue. By having a cognitive architecture that enhances FMs with Theory-of-Mind capabilities, our approach considers the mental states and perspectives of software makers. This allows our solution to iteratively clarify the beliefs, desires, and intentions of stakeholders, translating these into a set of refined requirements and a corresponding actionable natural language workflow in the often-overlooked requirements refinement phase of software engineering, which is crucial after initial elicitation. Through a multifaceted evaluation covering 150 diverse use cases, we demonstrate that our approach can accurately capture the intents and requirements of stakeholders, articulating them as both specifications and a step-by-step plan of action. Our findings suggest that the potential for significant improvements in the software development process justifies these investments. Our work lays the groundwork for future innovation in building intent-first development environments, where software makers can seamlessly collaborate with AIs to create software that truly meets their needs.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 30 of its 66 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

30 of 66 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024SpecRover: Code Intent Extraction via LLMs5 Aug
  2. 2024HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent31 May

Other references · 28

  1. 2024A Survey on LLM-as-a-Judgecited by 1,384
  2. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  3. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  4. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  5. 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 651
  6. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 480
  7. 2023Large Language Models Are State-of-the-Art Evaluators of Translation Qualitycited by 416
  8. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 397
  9. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 350
  10. 2024Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Modelscited by 301
  11. 2023Magicoder: Empowering Code Generation with OSS-Instructcited by 251
  12. 2024SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?cited by 196
16 more
  1. 2023An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generationcited by 193
  2. 2019Neural Text Summarization: A Critical Evaluationcited by 189
  3. 2025Preference Leakage: A Contamination Problem in LLM-as-a-judgecited by 119
  4. 2023Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilitiescited by 86
  5. 2023Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learningcited by 71
  6. 2023Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactionscited by 70
  7. 2024MuMA-ToM: Multi-modal Multi-Agent Theory of Mindcited by 51
  8. 2024Can LLMs Replace Manual Annotation of Software Engineering Artifacts?cited by 40
  9. 2024Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmapcited by 30
  10. 2022Mutual Theory of Mind for Human-AI Communicationcited by 15
  11. 2025Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolutioncited by 11
  12. 2024Output Format Biases in the Evaluation of Large Language Models for Code Translationcited by 9
  13. 2022The Use of NLP-Based Text Representation Techniques to Support Requirement Engineering Tasks: A Systematic Mapping Reviewcited by 5
  14. 2024Requirements Satisfiability with In-Context Learningcited by 5
  15. 2024Automatic Generation of Fashion Images using Prompting in Generative Machine Learning Modelscited by 2
  16. 2024What should I wear to a party in a Greek taverna? Evaluation for Conversational Agents in the Fashion Domaincited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026MeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networkscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Cognitive Agents Powered by Large Language Models for Agile Software Project Management
  2. 2026Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking
  3. 2026REprompt: Prompt Generation for Intelligent Software Development Guided by Requirements Engineering ↗
  4. 2025Enhancing Software Development with Context-Aware Conversational Agents: A User Study on Developer Interactions with Chatbots
  5. 2026Neuro-Symbolic Agents for Hallucination-Free Requirements Reuse
  6. 2025From Correctness to Collaboration: Toward a Human-Centered Framework for Evaluating AI Agent Behavior in Software Engineering
  7. 2025U2F: Encouraging SWE-Agent to Seize Novelty without Losing Feasibility
  8. 2025Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision