9 papers · 1 filter
ATLAS: Agentic Test-time Learning-to-Allocate Scaling
Peijia Qin, Qi Cao, Pengtao Xie
Test-time scaling has become a major way to improve large language model reasoning, but its orchestration has remained designer-engineered: a fixed sample budget, a fixed refinemen…
LLMs Know When They Know, but Do Not Act on It: A Metacognitive Harness for Test-time Scaling
Qi Cao, Yufan Wang, Peijia Qin +2
Large language models (LLMs) often expose useful signals of self-monitoring: before solving a problem, they can estimate whether they are likely to succeed, and after solving it, t…
Models Under SCOPE: Scalable and Controllable Routing via Pre-hoc Reasoning
Qi Cao, Shuhao Zhang, Ruizhe Zhou +3
Model routing chooses which language model to use for each query. By sending easy queries to cheaper models and hard queries to stronger ones, it can significantly reduce inference…
FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation
Ruiyi Zhang, Peijia Qin, Qi Cao +2
Code generation is a core application of large language models (LLMs), yet LLMs still frequently fail on complex programming tasks. Given its success in mathematical reasoning, tes…
DAJ: Data-Reweighted LLM Judge for Test-Time Scaling in Code Generation
Peijia Qin, Ruiyi Zhang, Qi Cao +1
Test-time scaling for code generation commonly relies on Best-of-N selection, in which multiple candidate solutions are sampled from a base model, and the best one is selected by a…
DreamPRM-Code: Function-as-Step Process Reward Model with Label Correction for LLM Coding
Ruiyi Zhang, Peijia Qin, Qi Cao +1
Process Reward Models (PRMs) have become essential for improving Large Language Models (LLMs) via test-time scaling, yet their effectiveness in coding remains limited due to the la…
DreamPRM-1.5: Unlocking the Potential of Each Instance for Multimodal Process Reward Model Training
Qi Cao, Pengtao Xie
Training multimodal process reward models (PRMs) is hard due to (i) distribution shift between training set and test set and (ii) quality imbalance across training data samples. Wh…
DreamPRM: Domain-Reweighted Process Reward Model for Multimodal Reasoning
Qi Cao, Ruiyi Wang, Ruiyi Zhang +2
Reasoning has substantially improved the performance of large language models (LLMs) on complicated tasks. Central to the current reasoning studies, Process Reward Models (PRMs) of…
MD tree: a model-diagnostic tree grown on loss landscape
Yefan Zhou, Jianlong Chen, Qinxue Cao +2
This paper considers "model diagnosis", which we formulate as a classification problem. Given a pre-trained neural network (NN), the goal is to predict the source of failure from a…