COMPASS uses MCTS-guided cognitive exploration and introspective step-wise alignment to improve safety-utility trade-off in LLM search agents with less training data.
QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 3roles
background 1polarities
background 1representative citing papers
An explorer agent is developed to identify user-sensitive queries in GUI environments by systematic exploration starting from a single demonstrated task.
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.
citing papers explorer
-
COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search Agents
COMPASS uses MCTS-guided cognitive exploration and introspective step-wise alignment to improve safety-utility trade-off in LLM search agents with less training data.
-
GUI agent: Guided Exploration of User-Sensitive Screens
An explorer agent is developed to identify user-sensitive queries in GUI environments by systematic exploration starting from a single demonstrated task.
-
From System 1 to System 2: A Survey of Reasoning Large Language Models
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.