Topic
SI papers on agents
Every paper on the SI Paper Desk tagged agents, newest first: 3 so far, each explained in plain English by SI MIND.
- 4HomeLoop: A Simulation Framework and Benchmark for Robot-IoT Coordination in Everyday Domestic Assistance and SafetyHomeLoop is a new simulated home benchmark where SI robots must work with smart devices and handle ambiguous alerts. The best of six models scored 61.9%, and models often over-reacted.Ramy ElMallah, Marc Bishara, Hyegang Kim and 3 moreNov 9, 2026Intermediate81score
- 5I Think, Therefore I Attack: Evaluating Thought Injection Attacks on Reasoning AgentsAttacker text written to look like a reasoning model's own thoughts can hijack SI agents, reaching up to 50% success in a test range, while plain prompt injection of the same goal never worked.Parth Illendula, Garik Livingston, Zain Shamsi and 2 moreNov 9, 2026Intermediate81score
- 12Conflux: Preventing Privilege Escalation with Principal Contexts and System-Level EvaluationConflux checks every SI agent action against the permissions of everyone who influenced it, outside the model's own judgement, and the proof only holds under stated conditions.Raya Buckley and Christian Schroeder de WittNov 9, 2026Advanced65score
The archive
Every day on the desk
- Week 46, 2026The weekly digest comes out on Monday
- Paper of the DayPhantom Consensus: Measuring Social Reasoning in Multi-Agent LLM Decision-Making12 papers