9 papers
How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks
Ali Ansari, Haoran Sun, Andy Zeyi Liu +48
Low reported scores on leading physics benchmarks, including those featured in the Artificial Analysis Intelligence Index (2026), suggest that frontier language models still strugg…
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…
Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework
Ziqiang Zhang, Jing Ma, Zilong Wang +6
Pricing automation in large-scale tourism is challenging because travel orders are highly unstructured, while pricing policies are complex, rapidly evolving, and inherently open-en…
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…
-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…
A Unified LLM-Adaptable Framework for Cold-Start Cognitive Diagnosis
Zihan Yao, Chentao Song, Yu He +4
Cognitive Diagnosis has become a critical task in AI-empowered education, supporting personalized learning by accurately assessing students' cognitive states. However, traditional…
ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis
Zeao Tu, Xiangdi Meng, Yu He +4
Large language models (LLMs) have shown remarkable effectiveness across various domains, with data augmentation methods utilizing GPT for synthetic data generation becoming prevale…
Scalable Model Editing via Customized Expert Networks
Zihan Yao, Yu He, Tianyu Qi +1
Addressing the issues of hallucinations and outdated knowledge in large language models is critical for their reliable application. Model Editing presents a promising avenue for mi…