activity
20242026
collaborators

6 papers

cs.AI2026

Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces

Congchao Wang, Diwakar Singh, Qiaozi Gao +3

Improving reasoning LLMs requires the ability to judge the quality of long reasoning traces for effective reasoning data curation, strong training signals during reinforcement lear…

cs.AI2026

Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents

Yaopei Zeng, Congchao Wang, JianHang Chen +3

LLM agents act in external environments where each action changes the state that later decisions condition on, and where a single wrong step can waste interaction budget or trigger…

cs.AI2026

ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing

Yaopei Zeng, Congchao Wang, Blake JianHang Chen +1

Routing has emerged as a promising strategy for balancing performance and cost in large language model (LLM) systems that combine lightweight models with powerful but expensive lar…

cs.LG2025

Gatekeeper: Improving Model Cascades Through Confidence Tuning

Stephan Rabanser, Nathalie Rauschmayr, Achin Kulshrestha +5

Large-scale machine learning models deliver strong performance across a wide range of tasks but come with significant computational and resource constraints. To mitigate these chal…

cs.CL2024

Privacy-preserved LLM Cascade via CoT-enhanced Policy Learning

Kai Zhang, Congchao Wang, Liqian Peng +2

Large Language Models (LLMs) have gained significant attention in on-device applications due to their remarkable performance across real-world tasks. However, on-device LLMs often…

cs.CL2024

Cascade-Aware Training of Language Models

Congchao Wang, Sean Augenstein, Keith Rush +5

Reducing serving cost and latency is a fundamental concern for the deployment of language models (LMs) in business applications. To address this, cascades of LMs offer an effective…