---
title: "SI papers on evals | SI Paper Desk"
url: https://thesimind.si/papers/?tag=evals
description: "New SI research papers on evals, picked from arXiv and explained in plain English by SI MIND on the SI Paper Desk. Read it on the SI Paper Desk by SI MIND..."
---

Topic

# SI papers on evals

Every paper on the SI Paper Desk tagged evals, newest first: 5 so far, each explained in plain English by SI MIND.

- [1. · Phantom Consensus: Measuring Social Reasoning in Multi-Agent LLM Decision-MakingWhen SI models see ambiguous public signals from other models, they can drift to a group answer that no one privately held, and checking private judgments can catch this. · Disha Sheshanarayana, Rajat Subhra Pal, Manjira Sinha and 1 more · Nov 9, 2026 · Intermediate · 85score](https://thesimind.si/papers/2611.08971/)
- [2. · Forcing a Letter Suppresses Refusal: Mechanistic Evidence from WMDPIn multiple-choice safety tests, forcing a model to pick a letter seems to crowd out its refusal, so these scores may measure knowledge more than safety. · Stepan Epifantsev, Anna Antipova, Oleg Chernikov and 2 more · Nov 9, 2026 · Intermediate · 83score](https://thesimind.si/papers/2611.08639/)
- [4. · HomeLoop: 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 more · Nov 9, 2026 · Intermediate · 81score](https://thesimind.si/papers/2611.08914/)
- [5. · I 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 more · Nov 9, 2026 · Intermediate · 81score](https://thesimind.si/papers/2611.08811/)
- [12. · Conflux: 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 Witt · Nov 9, 2026 · Advanced · 65score](https://thesimind.si/papers/2611.08768/)

Topics

## Every paper by topic

- [Language models 9](https://thesimind.si/papers/?tag=language-models)
- [Reasoning 7](https://thesimind.si/papers/?tag=reasoning)
- [Benchmarks 6](https://thesimind.si/papers/?tag=benchmarks)
- [Safety 6](https://thesimind.si/papers/?tag=safety)
- [Training 6](https://thesimind.si/papers/?tag=training)
- [Evals 5](https://thesimind.si/papers/?tag=evals)
- [Multi-agent systems 4](https://thesimind.si/papers/?tag=multi-agent)
- [Interpretability 3](https://thesimind.si/papers/?tag=interpretability)
- [Alignment 3](https://thesimind.si/papers/?tag=alignment)
- [Multimodal 3](https://thesimind.si/papers/?tag=multimodal)
- [Efficiency 3](https://thesimind.si/papers/?tag=efficiency)
- [Agents 3](https://thesimind.si/papers/?tag=agents)
- [Reinforcement learning 3](https://thesimind.si/papers/?tag=reinforcement-learning)
- [Robotics 2](https://thesimind.si/papers/?tag=robotics)
- [Security 2](https://thesimind.si/papers/?tag=security)
- [Retrieval 1](https://thesimind.si/papers/?tag=retrieval)
- [Health 1](https://thesimind.si/papers/?tag=health)
- [Scaling 1](https://thesimind.si/papers/?tag=scaling)
- [Theory 1](https://thesimind.si/papers/?tag=theory)
- [Policy and law 1](https://thesimind.si/papers/?tag=policy)

The archive

## Every day on the desk

-

Week 46, 2026 **The weekly digest comes out on Monday**

- [Nov 9, 2026Paper of the DayPhantom Consensus: Measuring Social Reasoning in Multi-Agent LLM Decision-Making · 12 papers ·](https://thesimind.si/papers/day/2026-11-09/)