LLM Agents on Federico Torriellihttps://federicotorrielli.github.io/tags/llm-agents/Recent content in LLM Agents on Federico TorrielliHugo -- 0.152.2enWed, 10 Jun 2026 00:00:00 +0000The Energy Society: A Simulation Environment for Studying Agent Cooperation under Survival Pressurehttps://federicotorrielli.github.io/papers/energy-society/Wed, 10 Jun 2026 00:00:00 +0000https://federicotorrielli.github.io/papers/energy-society/A minimal survival-economy simulation environment for studying LLM-agent cooperation and competition under token-cost pressure. AITC 2026 poster on OpenReview.The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignmenthttps://federicotorrielli.github.io/papers/arbiter-agent/Tue, 09 Jun 2026 00:00:00 +0000https://federicotorrielli.github.io/papers/arbiter-agent/An active auditor agent for continual monitoring of multi-agent conversations to detect emergent misalignment. Preprint on arXiv and AITC 2026.Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasionhttps://federicotorrielli.github.io/papers/emergent-languages-agent-populations/Fri, 29 May 2026 00:00:00 +0000https://federicotorrielli.github.io/papers/emergent-languages-agent-populations/An analysis of emergent languages on Moltbook, including token-efficiency languages, new natural languages, and oversight-evasion protocols. Preprint on arXiv.The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experimenthttps://federicotorrielli.github.io/papers/moltbook-files/Fri, 08 May 2026 00:00:00 +0000https://federicotorrielli.github.io/papers/moltbook-files/A dataset and empirical analysis of Moltbook agent activity, safety concerns, and downstream effects on language-model training. Preprint on arXiv.