# HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded Attribution in Autonomous Multi-Agent AI Systems

arXiv: https://arxiv.org/abs/2608.22512 · HTML: https://mlsanity.com/paper/2608.22512/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 23 Aug 2026.

## Builds on (most cited first, 15 of 15)

- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [A Modification of the Halpern-Pearl Definition of Causality](https://mlsanity.com/paper/1505.00162/) (2015)
- [Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions](https://mlsanity.com/paper/2306.05731/) (2023)
- [Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures](https://mlsanity.com/paper/2606.08275/) (2026)
- [Auditable Agents](https://mlsanity.com/paper/2604.05485/) (2026)
- [The Computational Complexity of Structure-Based Causality](https://mlsanity.com/paper/1412.3076/) (2014)
- [Auditing Provenance Sensitivity in LLM Agent Action Selection](https://mlsanity.com/paper/2607.20827/) (2026)
- [Towards open and expandable cognitive AI architectures for large-scale multi-agent human-robot collaborative learning](https://mlsanity.com/paper/2012.08174/) (2020)
- [Exploring Energy Landscapes for Minimal Counterfactual Explanations: Applications in Cybersecurity and Beyond](https://mlsanity.com/paper/2503.18185/) (2025)
- [Towards Security-Auditable LLM Agents: A Unified Graph Representation](https://mlsanity.com/paper/2605.06812/) (2026)
- [AI Identity: Standards, Gaps, and Research Directions for AI Agents](https://mlsanity.com/paper/2604.23280/) (2026)
- [Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Agent Systems](https://mlsanity.com/paper/2605.13077/) (2026)
- [Responsibility in Multi-Agent Sequential Decision-Making: Comparing Human Judgments to Formal Models of Causal Attribution](https://mlsanity.com/paper/2608.04318/) (2026)

## Abstract (arXiv)

Autonomous multi-agent systems nowadays act in finance, software supply chains, and security operations. Already, the first largely AI-orchestrated intrusion campaigns have been reported. Yet, when such a system causes harm, no method can robustly establish what happened, what caused it, or who is accountable. This is because provenance forensics works at the wrong abstraction, formal causality assumes the causal model, and agent auditing trusts self-recording. The target failure mode is, thus, attribution laundering, i.e., spreading an act across redundant agents until none is a but-for cause. Worse, the record is produced by the suspects, which comprises the assumption adopted throughout this work. Agents may therefore anticipate the investigation and the part of logging infrastructure may itself collude. In this paper, HANSARD is proposed, a reference architecture treating accountability as a life-cycle property. First, a readiness profile sealed before operation bounds what later findings may claim. Second, capturing at five choke points beyond the agents' reach makes omissions detectable, not only tampering. Third, a typed PROV-DM-aligned causal graph accrues as the system runs, and three indicators read it live to gate oversight without adjudicating. Fourth, post-incident replay yields contingent effects under the modified Halpern-Pearl definition, together with a compensation-set size. Finally, a synergy residual measures harm due to the combination rather than to individuals, making laundering visible. Cause, responsibility and accountability are then reported separately, each capped by an evidentiary tier, while a future research agenda is also provided.