Francesco Giarrusso
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Multiagent×1Society×1Crypto×1HCI×1
Frequent co-authors
Research Timeline
2026
Learning from Mistakes: Can LLM Self-Recover after Misalignment?
This paper shifts the focus of LLM safety from preventing misalignment to investigating the model's intrinsic ability to self-recover its alignment after being corrupted by adversarial inputs.
Draining the Energy Commons: Self-Defeating Over-Appropriation as a Coordination Failure in Agentic LLM Collectives
This paper studies coordination failures in a renewable energy commons among LLMs acting as electricity prosumers, finding that populations protect current service while undermining future service.
Highlighted terms show continued research focus across papers
Papers
cs.MAEmpiricalRecentJul 24, 2026
Draining the Energy Commons: Self-Defeating Over-Appropriation as a Coordination Failure in Agentic LLM Collectives
This paper studies coordination failures in a renewable energy commons among LLMs acting as electricity prosumers, finding that populations protect current service while undermining future service.
View →
cs.CYcs.CRcs.HCRecent