# From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems

arXiv: https://arxiv.org/abs/2210.02260 · HTML: https://mlsanity.com/paper/2210.02260/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 127 references that are in the map.
- First posted on arXiv 5 Oct 2022.

## Builds on (most cited first, 20 of 20)

- [Robots that can adapt like animals](https://mlsanity.com/paper/1407.3501/) (2014)
- [Empirical Evaluation of Abstract Argumentation: Supporting the Need for Bipolar and Probabilistic Approaches](https://mlsanity.com/paper/1707.09324/) (2017)
- [Blameworthiness in Strategic Games](https://mlsanity.com/paper/1809.05485/) (2018)
- [Together We Know How to Achieve: An Epistemic Logic of Know-How](https://mlsanity.com/paper/1705.09349/) (2017)
- [QED: using Quality-Environment-Diversity to evolve resilient robot swarms](https://mlsanity.com/paper/2003.02341/) (2020)
- [Stable Matching with Uncertain Linear Preferences](https://mlsanity.com/paper/1607.02917/) (2016)
- [Rapidly adapting robot swarms with Swarm Map-based Bayesian Optimisation](https://mlsanity.com/paper/2012.11444/) (2020)
- [Explicit Explore, Exploit, or Escape (E4): near-optimal safety-constrained reinforcement learning in polynomial time](https://mlsanity.com/paper/2111.07395/) (2021)
- [Strategic Coalitions with Perfect Recall](https://mlsanity.com/paper/1707.04298/) (2017)
- [Lifetime policy reuse and the importance of task capacity](https://mlsanity.com/paper/2106.01741/) (2021)
- [Intelligence in Strategic Games](https://mlsanity.com/paper/1910.07298/) (2019)
- [A Polynomial-time Decentralised Algorithm for Coordinated Management of Multiple Intersections](https://mlsanity.com/paper/2205.00877/) (2022)
- [Pareto Optimal Matchings in Many-to-Many Markets with Ties](https://mlsanity.com/paper/1507.02866/) (2015)
- [Subjective Logic Operators in Trust Assessment: an Empirical Study](https://mlsanity.com/paper/1312.4828/) (2013)
- [Size versus truthfulness in the House Allocation problem](https://mlsanity.com/paper/1404.5245/) (2014)
- [Armstrong's Axioms and Navigation Strategies](https://mlsanity.com/paper/1707.04106/) (2017)
- [Solving Hard Stable Matching Problems Involving Groups of Similar Agents](https://mlsanity.com/paper/1708.04109/) (2017)
- [Duty to Warn in Strategic Games](https://mlsanity.com/paper/1912.02759/) (2019)
- [Mechanism Design for Efficient Online and Offline Allocation of Electric Vehicles to Charging Stations](https://mlsanity.com/paper/2007.09715/) (2020)
- [A Polynomial-time, Truthful, Individually Rational and Budget Balanced Ridesharing Mechanism](https://mlsanity.com/paper/2105.11292/) (2021)

## Built on by (most cited first, 4 of 4)

- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Distributionally Robust Statistical Verification with Imprecise Neural Networks](https://mlsanity.com/paper/2308.14815/) (2023)
- [Simulating Human-Like Learning Dynamics with LLM-Empowered Agents](https://mlsanity.com/paper/2508.05622/) (2025)
- [Local-First Intelligence via Proactive SLM Collaborating with Feedback-Providing LLM](https://mlsanity.com/paper/2604.17827/) (2026)

## Abstract (arXiv)

The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on recent work and open research challenges in developing trustworthy autonomous systems and deploying human-centred AI systems that aim to support societal good.