VeriOS-Agent is an OS agent that proactively queries humans in untrustworthy scenarios via a query-driven framework and three-stage training, achieving 19.72% higher step-wise success rate over baselines while preserving normal performance.
Towards end-to-end embodied decision making via multi-modal large language model: Explorations with gpt4-vision and beyond
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Math-Shepherd is an automatically trained process reward model that scores solution steps to verify and reinforce LLMs, lifting Mistral-7B from 77.9% to 89.1% on GSM8K and 28.6% to 43.5% on MATH.
ASSCG is an RWKV-based adaptive gate trained with SFT and GRPO-style RL that makes Query/Cache/Drop decisions for slow LLM guidance in fast-slow autonomous driving planners, improving scores and cutting latency on nuPlan and NAVSIM.
citing papers explorer
-
VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents
VeriOS-Agent is an OS agent that proactively queries humans in untrustworthy scenarios via a query-driven framework and three-stage training, achieving 19.72% higher step-wise success rate over baselines while preserving normal performance.
-
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
Math-Shepherd is an automatically trained process reward model that scores solution steps to verify and reinforce LLMs, lifting Mistral-7B from 77.9% to 89.1% on GSM8K and 28.6% to 43.5% on MATH.
-
ASSCG: Just-Right Gating over Chattering for Fast-Slow LLM Planning in Autonomous Driving
ASSCG is an RWKV-based adaptive gate trained with SFT and GRPO-style RL that makes Query/Cache/Drop decisions for slow LLM guidance in fast-slow autonomous driving planners, improving scores and cutting latency on nuPlan and NAVSIM.