December 29, 2025 – January 4, 2026: 6 frontier papers out of 1,216 read.
Papers rated as moving the field
How we choose“Extensive experiments reveal that even state-of-the-art long-context LLMs struggle as input length increases, and standard retrieval-augmented generation systems collapse entirely.”
The authors, in the abstract
A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning
“Experiments on multiple benchmarks demonstrate that our method consistently outperforms state-of-the-art GRMs trained with outcome-only reward, confirming the superiority of integrating natural language over binary human feedback as supervision.”
“Experiments reveal that closed-source models significantly outperform open-source models (48.4% vs 32.1%).”
“Experiments on five mathematical benchmarks demonstrate that TNT reduces token usage by around 50% compared to DeepSeek-R1-Distill-Qwen-1.5B/7B and DeepScaleR-1.5B, while significantly improving accuracy.”
“Our results demonstrate a 100% success rate for atomic action hijacking and the ability to orchestrate high-impact exploits, including unauthorized file deletion, SMS transmission, and app uninstallation, without the attacker holding any corresponding permissions.”
Dec 29, 2025 – Jan 4, 2026: 47 cleared, 6 frontier
The week’s papers have not been sorted into fields yet.
Papers this week that name the model
Papers this week with an author at the lab
41 papers