# Adaptive Accountability in Networked MAS: Tracing and Mitigating Emergent Norms at Scale

arXiv: https://arxiv.org/abs/2512.18561 · HTML: https://mlsanity.com/paper/2512.18561/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 81 references that are in the map.
- First posted on arXiv 21 Dec 2025.

## Builds on (most cited first, 23 of 23)

- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [A Survey and Critique of Multiagent Deep Reinforcement Learning](https://mlsanity.com/paper/1810.05587/) (2018)
- [Principles alone cannot guarantee ethical AI](https://mlsanity.com/paper/1906.06668/) (2019)
- [Visibility into AI Agents](https://mlsanity.com/paper/2401.13138/) (2024)
- [TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems](https://mlsanity.com/paper/2506.04133/) (2025)
- [Emergence of Social Norms in Generative Agent Societies: Principles and Architecture](https://mlsanity.com/paper/2403.08251/) (2024)
- [Distributed Constraint Optimization Problems and Applications: A Survey](https://mlsanity.com/paper/1602.06347/) (2016)
- [Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game](https://mlsanity.com/paper/2305.12872/) (2023)
- [Rethinking the Reliability of Multi-agent System: A Perspective from Byzantine Fault Tolerance](https://mlsanity.com/paper/2511.10400/) (2025)
- [Learning and Sustaining Shared Normative Systems via Bayesian Rule Induction in Markov Games](https://mlsanity.com/paper/2402.13399/) (2024)
- [Causal Explanations for Sequential Decision-Making in Multi-Agent Systems](https://mlsanity.com/paper/2302.10809/) (2023)
- [Monitored Markov Decision Processes](https://mlsanity.com/paper/2402.06819/) (2024)
- [MACCA: Offline Multi-agent Reinforcement Learning with Causal Credit Assignment](https://mlsanity.com/paper/2312.03644/) (2023)
- [Norm Enforcement with a Soft Touch: Faster Emergence, Happier Agents](https://mlsanity.com/paper/2401.16461/) (2024)
- [Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making](https://mlsanity.com/paper/2410.12539/) (2024)
- [LumiMAS: A Comprehensive Framework for Real-Time Monitoring and Enhanced Observability in Multi-Agent Systems](https://mlsanity.com/paper/2508.12412/) (2025)
- [Analysing the Sample Complexity of Opponent Shaping](https://mlsanity.com/paper/2402.05782/) (2024)
- [Measuring Responsibility in Multi-Agent Systems](https://mlsanity.com/paper/2411.00887/) (2024)
- [Operationalising Rawlsian Ethics for Fairness in Norm-Learning Agents](https://mlsanity.com/paper/2412.15163/) (2024)
- [Chronology of Multi-Agent Interactions for Provenance of Evolving Information](https://mlsanity.com/paper/2504.12612/) (2025)

## Abstract (arXiv)

Large-scale networked multi-agent systems increasingly underpin critical infrastructure, yet their collective behavior can drift toward undesirable emergent norms such as collusion, resource hoarding, and implicit unfairness. We present the Adaptive Accountability Framework (AAF), an end-to-end runtime layer that (i) records cryptographically verifiable interaction provenance, (ii) detects distributional change points in streaming traces, (iii) attributes responsibility via a causal influence graph, and (iv) applies cost-bounded interventions-reward shaping and targeted policy patching-to steer the system back toward compliant behavior. We establish a bounded-compromise guarantee: if the expected cost of intervention exceeds an adversary's expected payoff, the long-run fraction of compromised interactions converges to a value strictly below one. We evaluate AAF in a large-scale factorial simulation suite (87,480 runs across two tasks; up to 100 agents plus a 500-agent scaling sweep; full and partial observability; Byzantine rates up to 10%; 10 seeds per regime). Across 324 regimes, AAF lowers the executed compromise ratio relative to a Proximal Policy Optimization baseline in 96% of regimes (median relative reduction 11.9%) while preserving social welfare (median change 0.4%). Under adversarial injections, AAF detects norm violations with a median delay of 71 steps (interquartile range 39-177) and achieves a mean top-ranked attribution accuracy of 0.97 at 10% Byzantine rate.