Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability that modern language models increasingly require but do not natively encode. While prior work uses reinforcement learning or test-time training, planning remains external to the model architecture. We formulate reasoning as optimal control and introduce the Test-Time Control (TTC) layer, which performs finite-horizon LQR planning over latent states at inference time, represents a value function within neural architectures, and leverages it as the nested objective to enable planning before prediction. To ensure scalability, we derive a hardware-efficient LQR solver based on a symplectic formulation and implement it as a fused CUDA kernel, enabling parallel execution with minimal overhead. Integrated as an adapter into pretrained LLMs, TTC layers improve mathematical reasoning performance by up to +27.8% on MATH-500 and 2-3x Pass@8 improvements on AMC and AIME, demonstrating that embedding optimal control as an architectural component provides an effective and scalable mechanism for reasoning beyond test-time training.
Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning
Sydney AI Centre, The University of Sydney（悉尼大学悉尼人工智能中心）；Australian Institute for Machine Learning, Adelaide University（阿德莱德大学澳大利亚机器学习研究所）；Australian Artificial Intelligence Institute, University of Technology Sydney（悉尼科技大学澳大利亚人工智能研究所）；Wuhan University（武汉大学）；School of Mathematics and Statistics, The University of Melbourne（墨尔本大学数学与统计学院）
Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS)（智能信息处理重点实验室，计算技术研究所，中国科学院）；Key Laboratory of AI Safety, Chinese Academy of Sciences（人工智能安全重点实验室，中国科学院）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）；Li Auto Inc.（利亚德公司）
HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling
The Chinese University of Hong Kong.（香港中文大学）；Pengcheng Laboratory.（鹏城实验室）；WeChat AI, Tencent（微信AI，腾讯）；University of Chinese Academy of Sciences.（中国科学院大学）
Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoning
Tencent Youtu Lab（腾讯优图实验室）；Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin, EIT, Ningbo, China（浙江省工业智能与数字孪生重点实验室）；Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China（香港理工大学计算学系）；Shenzhen Loop Area Institute, Shenzhen, China（深圳市环区研究所）
