MOA applies multi-objective RL with fine-grained rubrics and thought-augmented rollouts to role-playing agents, enabling an 8B model to match closed-source performance on PersonaGym and RoleMRC benchmarks.
arXiv preprint arXiv:2502.16940
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2025 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
LRMs underperform on simple system 1 questions in both accuracy and efficiency, with problem difficulty implicitly encoded in early hidden states.
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.
citing papers explorer
-
MOA: Multi-Objective Alignment for Role-Playing Agents
MOA applies multi-objective RL with fine-grained rubrics and thought-augmented rollouts to role-playing agents, enabling an 8B model to match closed-source performance on PersonaGym and RoleMRC benchmarks.
-
Exploring the System 1 Thinking Capability of Large Reasoning Models
LRMs underperform on simple system 1 questions in both accuracy and efficiency, with problem difficulty implicitly encoded in early hidden states.
-
Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.