collaborators

9 papers

cs.CR2026

Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense

Shuhao Zhang, Jiarui Li, Qi Cao +2

Prompt-injection detectors are heterogeneous: each is strong on a different slice of attacks, and none is always reliable. Yet existing systems still treat detection as a fixed sin…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…