# Argumentative Human-AI Decision-Making: Toward AI Agents That Reason With Us, Not For Us

arXiv: https://arxiv.org/abs/2603.15946 · HTML: https://mlsanity.com/paper/2603.15946/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 4 of its 62 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)
- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 4 of 4)

- [Large Language Models in Argument Mining: A Survey](https://mlsanity.com/paper/2506.16383/) (2025)
- [PeerArg: Argumentative Peer Review with LLMs](https://mlsanity.com/paper/2409.16813/) (2024)
- [MArgE: Meshing Argumentative Evidence from Multiple Large Language Models for Justifiable Claim Verification](https://mlsanity.com/paper/2508.02584/) (2025)
- [Towards Dialogues for Joint Human-AI Reasoning and Value Alignment](https://mlsanity.com/paper/2405.18073/) (2024)

## Built on by (most cited first, 2 of 2)

- [Discourse-Aware Policy Analysis with Argumentation: A Hybrid LLM-Symbolic Framework for Disaster Governance](https://mlsanity.com/paper/2607.13260/) (2026)
- [OmouAI: Argumentative Human-AI Policy Deliberation with Simulated Personas](https://mlsanity.com/paper/2609.31078/) (2026)

## Abstract (arXiv)

Computational argumentation offers formal frameworks for transparent, verifiable reasoning but has traditionally been limited by its reliance on domain-specific information and extensive feature engineering. In contrast, LLMs excel at processing unstructured text, yet their opaque nature makes their reasoning difficult to evaluate and trust. We argue that the convergence of these fields will lay the foundation for a new paradigm: Argumentative Human-AI Decision-Making. We analyze how the synergy of argumentation framework mining, argumentation framework synthesis, and argumentative reasoning enables agents that do not just justify decisions, but engage in dialectical processes where decisions are contestable and revisable -- reasoning with humans rather than for them. This convergence of computational argumentation and LLMs is essential for human-aware, trustworthy AI in high-stakes domains.