技术雷达 · 2026-09-10

G GitHub 新星 10 条

A arXiv 论文 10 条

1 TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model cs.ROcs.AI
We study the problem of navigating cluttered indoor environments with a humanoid robot. Unlike conventional methods that model navigation as a 2D path planning problem, humanoid traversal in cluttered
Anqi Li, Yuxin Chen, Zhaobo Li
2 Learning Length-Extrapolatable Recurrent Models cs.LGcs.CL
Recurrent models provide a natural path to long-context modeling, yet models trained with backpropagation through time (BPTT) often fail beyond their training horizon. Classical analyses emphasize gra
Hanwen Jiang
3 Procedural Graphs: Self-Evolving Execution Structures for LLM Agents cs.AIcs.CLcs.MA
Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. Most agents select actions through unconstrained generation over an accumulating
Yuxing Lu, Yicheng Chen, Shanchan Wu
4 Silver Rate Is (Almost) Optimal for Gradient Descent Acceleration math.OCcs.LG
We study how far gradient descent (GD) can be accelerated by predetermined nonnegative stepsizes in smooth convex optimization. Writing $p_{\mathrm{sil}}=\log_2(1+\sqrt{2})$, we prove an $Ω\left(n^{-p
Yuhan Ye, Kaizhao Liu
5 NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and Forecasting cs.LGcs.AI
The digitization of healthcare has generated vast, longitudinal, and multimodal patient records over a lifetime, yet fully exploiting these data to represent and predict patient state trajectories rem
Tobias Susetzky, Raphael Rehms, Dmitrii Seletkov
6 A Data-Driven Framework for Identifying and Prioritizing RPA Opportunities in Healthcare Processes cs.AIcs.CL
Robotic Process Automation (RPA) is widely used to reduce administrative burden in United States hospitals, yet an estimated 30-50% of RPA initiatives underperform because processes are selected infor
Maria Alejandra Gomez, Juan Manuel Castillo
7 Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation cs.LGcs.CL
Existing methods for test-time reinforcement learning (TTRL) derive rewards from answer-level self-voting on unlabeled test-time tasks with canonical answers, but this breaks down for code generation
Jiacheng Xu, Feng Chen, Xiuneng Xu
8 Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails cs.AI
Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a critical determinant of agentic task success. Automated harness evolution can en
Zhou Yu, Bin Bi, Shiva Kumar Pentyala
9 ExecCritic: Learn to Test, Test to Improve for Coding Agents cs.AIcs.CLcs.SE
Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue. Agent-generated tests can encode incomplete or incorr
Leitian Tao, Baolin Peng, Haorui Wang
10 Nearly Tight Rademacher Bounds for Sparsely Activated Neural Networks cs.LGstat.ML
An input may activate few hidden units even when different inputs collectively use an entire network. We study the statistical complexity of this input-dependent sparsity in the one-hidden-layer ReLU
Xiaoyu Li, Zhizhou Sha, Jiaojiao Jiang

H Hacker News 10 条