12 papers
Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance
Wenhao Chen, Sirui Sun, Shengyuan Bai +1
Aligning large language models (LLMs) with human values typically relies on post-training or inference-time steering that directly manipulates the backbone's parameters or represen…
Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
Haonan Dong, Qiguan Feng, Kehan Jiang +3
Autonomous agents have rapidly matured as task executors and seen widespread deployment via harnesses such as OpenClaw. Safety concerns have rightly drawn growing research attentio…
Context-Value-Action Architecture for Value-Driven Large Language Model Agents
TianZe Zhang, Sirui Sun, Yuhang Xie +3
Large Language Models (LLMs) have shown promise in simulating human behavior, yet existing agents often exhibit behavioral rigidity, a flaw frequently masked by the self-referentia…
NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons
Haonan Dong, Kehan Jiang, Haoran Ye +3
Large Reasoning Models (LRMs) have recently achieved remarkable success in complex reasoning tasks. However, closer scrutiny reveals persistent failure modes compromising performan…
FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models
Kehan Jiang, Haonan Dong, Zhaolu Kang +2
Recent Large Reasoning Models (LRMs) like DeepSeek-R1 have demonstrated remarkable success in complex reasoning tasks, exhibiting human-like patterns in exploring multiple alternat…
Large Language Model Psychometrics: A Systematic Review of Evaluation, Validation, and Enhancement
Haoran Ye, Jing Jin, Yuhang Xie +2
The advancement of large language models (LLMs) has outpaced traditional evaluation methodologies. This progress presents novel challenges, such as measuring human-like psychologic…