project Overview & Details src Code Repositories publications See Our Papers

Principled Role Assignment for Deliberative Reasoning with Multi-Agent LLMs in a Metacognitive Architecture

IJCAI-ECAI 2026 — Demonstrations Track — Bremen, Germany — August 15–21, 2026
Ricky J. Sethi1,2,3, Charles Courchaine1,3, Hefei Qiu1
1Fitchburg State University   2Worcester Polytechnic Institute   3National University

Abstract

We present a principled five-role architecture for multi-agent deliberative reasoning. Unlike existing frameworks that assign roles through ad-hoc domain metaphors or simple adversarial pairings, our system draws upon validated team-role taxonomies (Mumford et al., 2006; Belbin, 1993; Mathieu et al., 2014), dialectical reasoning (Schwenk, 1990), and metacognitive monitoring theory (Nelson & Narens, 1990) to compute a five-dimensional Metacognitive State Vector (MSV) for each agent, apply role-specific fitness functions, and assign globally optimal agent-roles via the Hungarian algorithm.

The demonstration system runs entirely offline using multiple local LLMs and provides real-time visualization of routing decisions, fitness matrices, dialectical pipeline stages, and MSV evolution.

Two principled departures distinguish this work: separating the Evaluator from the Critic to enable explicit meta-level monitoring distinct from object-level adversarial critique, grounded in Nelson & Narens' two-level metacognitive architecture; and positioning the Generalist outside the dialectical chain as a boundary-spanning orchestrator, grounded in the TREO framework.

Demo Video

The video demonstrates:

  • MSV-based routing correctly discriminating simple factual queries (System 1) from complex contested queries (System 2);
  • two new roles innovated as principled departures grounded in team science and dialectical philosophy;
  • the full four-stage dialectical pipeline—Expert, Critic, Evaluator, Synthesizer—producing substantively different content at each stage;
  • the heterogeneous fitness matrix using MSV-derived fitness functions and Hungarian-optimal role assignment; and
  • explainability dashboard with MSV evolution across pipeline stages showing Correctness Evaluation increasing and Conflicting Information resolving through the dialectical process.

System Architecture

Five-role architecture for multi-agent deliberative reasoning
Figure 1: Five-role architecture. The Generalist (Orchestrating Observer) operates outside the dialectical chain. The four core roles execute sequentially: Expert (Thesis) → Critic (Antithesis) → Evaluator (Resolution) → Synthesizer (Synthesis).

The five roles are derived from the intersection of dialectical philosophy, team role theory, and metacognitive science:

  • Domain Expert (Thesis) — Mumford et al.'s Contributor: generates the initial response
  • Critic (Antithesis) — Mumford et al.'s Critic: adversarial devil's advocacy at the object level
  • Evaluator (Resolution) — Novel departure: meta-level monitoring of the thesis-antithesis exchange quality, grounded in Nelson & Narens (1990)
  • Synthesizer (Synthesis) — Mumford et al.'s Completer: integrates refined perspectives
  • Generalist (Orchestrating Observer) — Novel departure: boundary-spanning orchestrator from TREO framework (Mathieu et al., 2014)

Implementation

The system is implemented as a self-contained Python package (~2,100 lines across 12 modules) that extends an existing FastAPI/HTMX dual-process chat platform. The backend connects to local LLM instances via Ollama (currently Llama 3.2 and Qwen variants), enabling fully offline operation with no API dependencies.

External dependencies: SciPy (Hungarian algorithm), NumPy, Bokeh (visualization).

Source code: https://github.com/wpiresearch/metis-llm-src/tree/main/ijcai-msv-2026

Presentation Materials

Materials from the IJCAI-ECAI 2026 demo presentation in Bremen.

  • Demo Talk Slides (10 min): [PDF]

Related Publications

  • IJCAI-ECAI 2026 (this work): Ricky J. Sethi, Charles Courchaine, and Hefei Qiu, “Principled Role Assignment for Deliberative Reasoning with Multi-Agent LLMs in a Metacognitive Architecture.” Demonstrations Track, IJCAI-ECAI 2026. [PDF]
  • TheWebConf 2026: Charles Courchaine*, Ricky J. Sethi*, and Hefei Qiu, “Implementation of a Metacognition Framework for Self-Awareness and Self-Regulation in Ensembles of LLMs.” ACM Proceedings of The Web Conference (TheWebConf), 2026. (* Equal contribution) [PDF]
  • CIKM 2025: Ricky J. Sethi, Hefei Qiu, Charles Courchaine, and Joshua Iacoboni, “Do LLMs Dream of Electric Emotions? Towards Quantifying Metacognition and Generalizing the Teacher-Student Model Using Ensembles of LLMs.” ACM International Conference on Information and Knowledge Management (CIKM), 2025. [ACM DL] [PDF]

Funding: Supported in part by a Google Cloud Research Grant (November 2025).

Contact

For questions about this work, please contact rickys@sethi.org.


← Back to Metacognition Research home