# BoardroomAI: Dependency-Aware Human-Steerable Multi-Agent Deliberation through Evolving Decision Graphs

arXiv: https://arxiv.org/abs/2608.13046 · HTML: https://mlsanity.com/paper/2608.13046/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Builds on (most cited first, 11 of 11)

- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?](https://mlsanity.com/paper/2402.18272/) (2024)
- [Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate](https://mlsanity.com/paper/2305.11595/) (2023)
- [Appropriate Reliance on AI Advice: Conceptualization and the Effect of Explanations](https://mlsanity.com/paper/2302.02187/) (2023)
- [Designing Creative AI Partners with COFI: A Framework for Modeling Interaction in Human-AI Co-Creative Systems](https://mlsanity.com/paper/2204.07666/) (2022)
- [Towards Human-AI Deliberation: Design and Evaluation of LLM-Empowered Deliberative AI for AI-Assisted Decision-Making](https://mlsanity.com/paper/2403.16812/) (2024)
- [An Ontology of Co-Creative AI Systems](https://mlsanity.com/paper/2310.07472/) (2023)
- [From Debate to Deliberation: Structured Collective Reasoning with Typed Epistemic Acts](https://mlsanity.com/paper/2603.11781/) (2026)
- [Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations](https://mlsanity.com/paper/2605.14175/) (2026)
- [LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph Retrieval](https://mlsanity.com/paper/2606.28379/) (2026)

## Abstract (arXiv)

Organizational decisions are co-created while evidence, constraints, and human priorities continue to evolve. In conventional transcript-based multi-agent systems, humans typically provide an initial problem, agents deliberate internally, and the system returns a final response. BoardroomAI instead treats the human as a persistent participant who can intervene by challenging assumptions, modifying constraints, changing priorities, introducing evidence, or redirecting the decision process. We operationalize this human--agent coexistence through four components: (i) a typed decision graph representing evidence, assumptions, constraints, claims, objections, alternatives, risks, decisions, semantic dependencies, and specialist responsibility; (ii) an intervention compiler that converts confirmed human actions into explicit graph updates; (iii) dependency-aware propagation that identifies affected subgraphs, preserves unaffected artifacts, and selectively reactivates relevant specialists; and (iv) an evaluation framework measuring intervention impact, repair coverage, preservation, recomputation, and decision validity. Across 600 generated decision-DAG interventions, propagation matched exhaustive impact computation while inspecting only 14.59% of nodes. In a 12-case exploratory pilot, selective repair recomputed 62.11% of canonical nodes, preserved all gold-unaffected nodes, and produced valid updated decisions in six cases while abstaining in the remaining six. These abstentions show that correct intervention routing may still provide insufficient context for synthesis, motivating a decision-sufficient context closure for human-steered multi-agent deliberation. All results are synthetic and prototype-level.