Scheduling Your LLM Reinforcement Learning with Reasoning Trees
arXiv:2510.24832v1 Announce Type: new Abstract: Using Reinforcement Learning with Verifiable Rewards (RLVR) to optimize Large Language Models (LLMs) can be…
NeuroPathNet: Dynamic Path Trajectory Learning for Brain Functional Connectivity Analysis
arXiv:2510.24025v2 Announce Type: replace-cross Abstract: Understanding the evolution of brain functional networks over time is of great significance for the…
FaCT: Faithful Concept Traces for Explaining Neural Network Decisions
arXiv:2510.25512v1 Announce Type: cross Abstract: Deep networks have shown remarkable performance across a wide range of tasks, yet getting a…
Reflections on the Reproducibility of Commercial LLM Performance in Empirical Software Engineering Studies
arXiv:2510.25506v1 Announce Type: cross Abstract: Large Language Models have gained remarkable interest in industry and academia. The increasing interest in…
What Work is AI Actually Doing? Uncovering the Drivers of Generative AI Adoption
arXiv:2510.23669v2 Announce Type: replace-cross Abstract: Purpose: The rapid integration of artificial intelligence (AI) systems like ChatGPT, Claude AI, etc., has…
Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents
arXiv:2510.23691v1 Announce Type: new Abstract: We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored…
BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents
arXiv:2510.23458v2 Announce Type: replace-cross Abstract: Confidence in LLMs is a useful indicator of model uncertainty and answer reliability. Existing work…