10 papers
Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization
Xianlei Zhou, Xiangdi Meng, Yu He +7
Policy optimization (PO) for Large Language Models faces a stability--exploration trade-off, currently mediated by an action-side Policy-KL regularizer. This puts practitioners in…
Dissecting Failure Dynamics in Large Language Model Reasoning
Wei Zhu, Jian Zhang, Lixing Yu +2
Large Language Models (LLMs) achieve strong performance through extended inference-time deliberation, yet how their reasoning failures arise remains poorly understood. By analyzing…
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aakshita Chandiramani +544
We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemo…
Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement
Jian Zhang, Zhangqi Wang, Zhiyuan Wang +5
Linguistic expressions of emotions such as depression, anxiety, and trauma-related states are pervasive in clinical notes, counseling dialogues, and online mental health communitie…
ErrEval: Error-Aware Evaluation for Question Generation through Explicit Diagnostics
Weiping Fu, Bifan Wei, Jingyi Hao +7
Automatic Question Generation (QG) often produces outputs with critical defects, such as factual hallucinations and answer mismatches. However, existing evaluation methods, includi…
-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation
Jian Zhang, Yu He, Zhiyuan Wang +5
Scientific reasoning relies not only on logical inference but also on activating prior knowledge and experiential structures. Memory can efficiently reuse knowledge and enhance rea…
MAXS: Meta-Adaptive Exploration with LLM Agents
Jian Zhang, Zhiyuan Wang, Zhangqi Wang +7
Large Language Model (LLM) Agents exhibit inherent reasoning abilities through the collaboration of multiple tools. However, during agent inference, existing methods often suffer f…
Toward Clinically Explainable AI for Medical Diagnosis: A Foundation Model with Human-Compatible Reasoning via Reinforcement Learning
Qika Lin, Yifan Zhu, Bin Pu +14
The clinical adoption of artificial intelligence (AI) in medical diagnostics is critically hampered by its black-box nature, which prevents clinicians from verifying the rationale…
MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning
Jian Zhang, Zhiyuan Wang, Zhangqi Wang +6
Collaborative reasoning with multiple agents offers the potential for more robust and diverse problem-solving. However, existing approaches often suffer from homogeneous agent beha…
MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization
Jian Zhang, Zhangqi Wang, Haiping Zhu +6
Large language models (LLMs) typically operate in a question-answering paradigm, where the quality of the input prompt critically affects the response. Automated Prompt Optimizatio…