Bayesian control for coding agents Theodore Papamarkou, Vladislav Smirnov, Viktor Mazanov, Artem Vazhentsev, Preslav Nakov, Timothy Baldwin, Artem Shelmanov https://t.co/1EUIZ7fmTy [ππ.π°πΈ ππ.π²π»] https://t.co/5sFFzguwnn
Who's Who of AI
Artificial Intelligence Papers
What they're sharing
Bayesian control for coding agents arxiv.org
Can Scale Save Us From Plasticity Loss in Large Language Models? arxiv.org
SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis arxiv.org
Reinforcement Learning Towards Broadly and Persistently Beneficial Models arxiv.org
SPIRAL: Learning to Search and Aggregate arxiv.org
DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models arxiv.org
Agent-as-a-Router: Agentic Model Routing for Coding Tasks arxiv.org
A Formula-Driven Survey and Research Agenda for On-Policy Distillation arxiv.org
Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards arxiv.org
VISTA Architect: A graph database-oriented health AI system demonstrated in multidisciplinary tumor boards arxiv.org
Grounded Scaling: Why Agentic AI Needs Deterministic Environments arxiv.org
Beyond Shapley: Efficient Computation of Asymmetric Shapley Values arxiv.org
Articles & links
Can Scale Save Us From Plasticity Loss in Large Language Models? J. Fernando Hernandez-Garcia, TomΓ‘s Figliolia, Beren Millidge https://t.co/rX82zG0aGV [ππ.π°πΈ] https://t.co/gza8ObQmpp
SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis Yucheng Yuan, Yuanfeng Ji, Zhongxiao Li, Ruijiang Li https://t.co/UXrVJURu5M [ππ.π°πΈ] π¬Accepted to ICML 2026 https://t.co/mv6BhLF8jL
Reinforcement Learning Towards Broadly and Persistently Beneficial Models Akshay V. Jagadeesh, Rahul K. Arora, Khaled Saab, Ali Malik, Mikhail Trofimov, Foivos Tsimpourlas, Johannes Heidecke, Karan Singhal https://t.co/Bd6xrwj5BN [ππ.π°πΈ ππ.π²π»] https://t.co/4FcHmEfg80
SPIRAL: Learning to Search and Aggregate Jubayer Ibn Hamid, Ifdita Hasan Orney, Michael Y. Li, Omar Shaikh, Yoonho Lee, Dorsa Sadigh, Chelsea Finn, Noah Goodman https://t.co/CRBpj1Mjhk [ππ.π°πΈ] https://t.co/kVEHyMHKpK
DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models Jungseob Lee, Seongtae Hong, Seungjun Lee, Jaehyung Seo, Junyoung Son, Sugyeong Eo, Chanjun Park, β¦ https://t.co/4OfjMyUCwq [ππ.π°πΈ ππ.π²π»] π¬Code: https://t.co/X5kZyWhmRU https:/β¦
Agent-as-a-Router: Agentic Model Routing for Coding Tasks Pengfei Zhou, Zhiwei Tang, Yixing Ma, Jiasheng Tang, Yizeng Han, Zhenglin Wan, Fanqing Meng, Wei Wang, Bohan Zhuang, Wangbo Zhao, Yang You https://t.co/LA6OAwFlc2 [ππ.π°πΈ] https://t.co/vf4PUnEp8r
A Formula-Driven Survey and Research Agenda for On-Policy Distillation Bowen Zhang https://t.co/cmgaRqZmmb [ππ.π°πΈ] https://t.co/kEQdgJ6Qeo
Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards Jungseob Lee, Seungyoon Lee, Seongtae Hong, Minhyuk Kim, Chanjun Park, β¦ https://t.co/p3b0ygS8Qt [ππ.π°πΈ ππ.π²π»] π¬Code: https://t.co/qK5JTlCFNR https://t.co/v4β¦
VISTA Architect: A graph database-oriented health AI system demonstrated in multidisciplinary tumor boards Tuomo Kiiskinen, Jason Fries, Philip Adamson, David Wu, β¦ https://t.co/FztYEvHRVn [ππ.π°πΈ ππ.π²π» ππ.π³π± ππ.πΈπ] π¬Code: https://t.co/delaPGK4mg https://t.co/fBV6d1tjfQ
Grounded Scaling: Why Agentic AI Needs Deterministic Environments Liang Ding, Xintong Wang https://t.co/nG7VwaUece [ππ.π°πΈ] https://t.co/MSplCha9Vz
Beyond Shapley: Efficient Computation of Asymmetric Shapley Values Ezequiel Companeetz, Santiago Cifuentes, Sergio Abriola https://t.co/08R4z67uYF [ππ.π°πΈ] https://t.co/Q2z6B9pupn