--- title: "SI papers on language models | SI Paper Desk" url: https://thesimind.si/papers/?tag=language-models description: "New SI research papers on language models, picked from arXiv and explained in plain English by SI MIND on the SI Paper Desk. Read it on the SI Paper Desk by..." --- Topic # SI papers on language models Every paper on the SI Paper Desk tagged language models, newest first: 9 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/) - [3. · AIM: Adaptive Interaction in Multi-Agent Debate for Multimodal LLM InferenceAIM lets SI agents in a debate choose, case by case, how to share evidence (text, graph, or image, audio and video regions), which raised accuracy and cut token use in the authors' tests. · Wei Fan, JinYi Yoon and Bo Ji · Nov 9, 2026 · Intermediate · 83score](https://thesimind.si/papers/2611.08950/) - [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/) - [6. · Alignment by Confident Debate: Preference Learning from Multi-Agent DebateAbCD turns debates among several SI models into training preferences without gold answer labels, and the authors report better accuracy than ensembling, debate alone, or SFT on the same traces. · Nikhil Verma, Dingxian Wang, Mohammad Reza Rezaei and 2 more · Nov 9, 2026 · Intermediate · 81score](https://thesimind.si/papers/2611.09568/) - [7. · ReSUM: Reasoning-Driven Multi-Agent Framework for Query-Focused SummarizationReSUM splits meeting summarization into planned steps handled by separate SI agents, and the authors say this gives more faithful summaries than one-pass methods. · Sonali, Deeksha Varshney and Asif Ekbal · Nov 9, 2026 · Intermediate · 81score](https://thesimind.si/papers/2611.09349/) - [9. · BrainCoT: A Multi-Task Zero-Shot Brain Signal Foundation Model with Neurometric-Anchored Chain-of-Thought ReasoningBrainCoT is a single brain signal model that handles several tasks with no extra training, and it gives step by step reasoning tied to measurable brain evidence. · Yiyu Gui, Mingzhi Chen, Guibo Luo and 1 more · Nov 9, 2026 · Intermediate · 73score](https://thesimind.si/papers/2611.09082/) - [10. · Cross-Layer TopK: Dynamically Allocating Sparsity Across Layers in TranscodersCross-Layer TopK sets one sparsity budget for the whole model and shifts it between layers during training, giving better reconstruction with fewer active latents on Qwen3-8B-Base. · Anyuan Zhuo, Shaohua Zhang, Tianle Li and 4 more · Nov 9, 2026 · Advanced · 71score](https://thesimind.si/papers/2611.09233/) - [11. · Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM ReasoningDR-BOLT trains one vision-language model to answer simple questions directly and think step by step only when needed, cutting wasted reasoning and training time. · Hongbin Lin, Sizhe Zou, Juangui Xu and 6 more · Nov 9, 2026 · Advanced · 70score](https://thesimind.si/papers/2611.09154/) 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/)