From Debate to Deliberation: Structured Collective Reasoning with Typed Epistemic Acts

Sunil Prakash

cs.AIMar 12, 2026

From Debate to Deliberation: Structured Collective Reasoning with Typed Epistemic Acts

Authors: Sunil Prakash

Organizations: Indian School of Business, India

Abstract

Multi-agent LLM systems increasingly tackle complex reasoning, yet their interaction patterns remain limited to voting, unstructured debate, or pipeline orchestration. None model deliberation: a phased process where differentiated participants exchange typed reasoning moves, preserve disagreements, and converge on accountable outcomes. We introduce Deliberative Collective Intelligence (DCI), specifying four reasoning archetypes, 14 typed epistemic acts, a shared workspace, and DCI-CF, a convergent flow algorithm that guarantees termination with a structured decision packet containing the selected option, residual objections, minority report, and reopen conditions. We evaluate on 45 tasks across seven domains using Gemini 2.5 Flash. On non-routine tasks (n=40), DCI significantly improves over unstructured debate (+0.95, 95% CI [+0.41, +1.54]). DCI excels on hidden-profile tasks requiring perspective integration (9.56, highest of any system on any domain) while failing on routine decisions (5.39), confirming task-dependence. DCI produces 100% structured decision packets and 98% minority reports, artifacts absent from all baselines. However, DCI consumes ~62x single-agent tokens, and single-agent generation outperforms DCI on overall quality. DCI's contribution is not that more agents are better, but that consequential decisions benefit from deliberative structure when process accountability justifies the cost.

Figures & tables

#	Act	Family	Description
1	frame	Orienting	Define how to view the problem
2	propose	Generative	Put forward a candidate idea or path
3	clarify	Orienting	Remove ambiguity or distinguish concepts
4	ask	Critical	Open a useful question
5	challenge	Critical	Test weakness, assumption, or consequence
6	extend	Generative	Build on another idea

Table 1: The 14 core epistemic acts in DCI ’s interaction grammar, organized by family.

Act Family	Cognitive Function	Failure if Absent
Orienting	Problem framing	Shallow or misdirected problem definition
Generative	Search breadth	Limited option space, premature lock-in
Critical	Assumption testing	False agreement, unexamined proposals
Integrative	Synthesis	Fragmentation, list of views without judgment
Epistemic	Confidence & revision	Fake certainty, no genuine belief update
Decisional	Closure	Endless discussion, no actionable outcome

Table 2: Act families, their cognitive functions, and the deliberation failure that occurs when the family is absent.

Figure 1: DCI-CF algorithm flow. Stages 3–6 form a loop bounded by max_rounds . If convergence fails after round exhaustion, Stage 7 provides a deterministic fallback. Every path terminates at Stage 8 with a structured decision packet.

System	$N$	Overall	Risk ID	Depth	Actionability
DCI (Ours)	45	8.24	8.84	8.62	8.96
B1: Single Agent	45	8.84	9.42	9.00	9.00
B3: Simple Voting	45	8.78	8.66	8.67	9.44
B4: Self-Consistency	45	8.65	8.37	8.53	9.32
B2: Unstructured Debate	45	7.75	8.39	7.72	8.76

Table 3: Main results across all seven evaluation domains (

N=

number of task evaluations per condition). Overall quality, risk identification, reasoning depth, and actionability scored 1–10 by LLM-as-judge (Gemini 3 Flash Preview). Bold indicates best in column.

System	Hidden-Prof.	Late-Evid.	Risk	Disagree.	Policy	Arch.	Routine
	n=5	n=5	n=5	n=5	n=10	n=10	n=5
DCI (Ours)	9.56	9.24	8.48	8.15	8.55	8.13	5.39
Single Agent	9.25	9.60	8.85	8.87	8.82	8.73	7.88
Voting	9.30	9.26	8.03	8.68	8.26	9.19	8.86
Self-Consistency	9.08	8.80	8.77	7.83	8.97	8.22	8.96
Unstr. Debate	9.03	8.45	7.83	8.24	8.03	5.78	8.58

Table 4: Overall quality scores by domain. Bold indicates best in each column.

n

= tasks per domain.

Metric	DCI	SA	Debate	Voting	SC
Decision packet	100%	1%	8%	16%	0%
Minority report	98%	0%	0%	0%	0%
Reopen conditions	100%	0%	0%	0%	0%
Explicit assumptions	3.6	3.3	0.2	0.0	0.0
Risk count	4.3	10.5	3.5	4.9	3.4
Objection count	3.8	7.3	1.1	2.4	2.2

Table 5: Process metrics across systems. Decision packet completeness, minority report presence, and reopen conditions presence are percentages. Explicit assumptions and risk/objection counts are means per task.

System	Mean Tokens	Quality	Quality/kToken
B1: Single Agent	3,809	8.84	2.320
B2: Unstructured Debate	9,458	7.75	0.819
B4: Self-Consistency	21,249	8.65	0.407
B3: Simple Voting	31,987	8.78	0.274
DCI (Ours)	237,565	8.24	0.035

Table 6: Efficiency metrics across systems. Mean tokens per task across all agents and rounds.

Condition	Overall	$\Delta$ vs. Full
Full DCI	8.24	—
A1: No Archetypes	8.61 $\pm$ 0.68	+0.37
A2: No Typed Grammar	8.32 $\pm$ 1.47	+0.08
A3: No DCI-CF	8.33 $\pm$ 0.91	+0.09

Table 7: Ablation results (

n=25

tasks each). Overall quality scored 1–10. Full DCI reference is the overall mean (

n=45

Condition	Gemini	GPT-4o	Claude
Voting	9.24	8.73	8.66
Single Agent	9.12	8.73	8.50
DCI	8.57	8.27	8.12
Self-Consistency	8.50	8.75	7.62
Unstructured Debate	6.97	8.06	7.54

Table 8: Cross-judge validation: mean overall quality (1–10) for 20 representative outputs scored by three independent LLM judges (4 outputs per condition).

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Parameter	Description	Value
DCI-CF Parameters
max_rounds	Maximum deliberation rounds	2
max_options	Maximum candidate options	5
finalist_count	Finalists for scoring	3
convergence_margin	Score dominance threshold $\epsilon$	0.15
fallback_rule	Forced-decision method	outranking

Appendix

Table 9: Experimental configuration parameters.

Explore similar work

LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability
Jul 7, 2026Chenxu Wang, Yongkun Yang, Boyuan Du +2LLM Agent Evaluation Multi-Agent Collaboration
Department of Computer Science and Technology, Tsinghua University · Fuzhou University
The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation
Jun 2, 2026Herun Wan, Jiaying Wu, Minnan Luo +4Multi-Agent LLM Systems LLM Agent Evaluation
Xi’an Jiaotong University · National University of Singapore · Yunnan University +1
The Deliberative Deficit: An Empirical Critique of LLMs in Democratic Discourse
Aug 10, 2026Maurice FlechtnerLLM Evaluation Multi-Agent Debate
University of Zurich, Zurich, Switzerland · ETH Zurich, Zurich, Switzerland

Jul 7, 2026J/K move · Enter open · S save

LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability

Chenxu Wang, Yongkun Yang, Boyuan Du, Shiwei Lin+1

Department of Computer Science and Technology, Tsinghua University · Fuzhou University

LLM Agent Evaluation Multi-Agent Collaboration AI Agent Benchmarks Multi-Agent Reasoning

Open paper AskPDF arXiv

Deliberation plays a crucial role in collaboration; when humans work together, they naturally engage in communication to align information and reach an agreement. In this paper, we investigate deliberative large language model (LLM) agents under partially observable joint decision-making tasks. We formalize deliberative collaboration as a cooperative joint decision problem with partial and asymmetric observations, and introduce a scalable benchmark that instantiates this problem across multiple task settings and domains in which agents must exchange information through deliberation to reach a joint decision with a shared reward. We then instantiate a reference scaffold and evaluation protocol for deliberative agents and conduct a systematic evaluation of a range of representative LLMs. The results reveal that complex deliberative collaboration tasks continue to challenge state-of-the-art language models. Even with the aid of external mathematical tools, language models may fail in either the deliberation process for aligning information or the complex reasoning process for making the decision. On the other hand, diagnostic analysis reveals that the deliberation process may also provide opportunities for reflection and error correction, sometimes improving performance over centralized baselines. Altogether, our work establishes a foundation for evaluating and improving LLM agents in deliberative collaboration and provides insights into the strengths, limitations, and properties of current LLM-based multi-agent systems.

Abstract

Explore similar work

LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability

The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation

The Deliberative Deficit: An Empirical Critique of LLMs in Democratic Discourse