From the 2 of 5 linked papers with an AI index.
5 papers
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…
Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents
Yaopei Zeng, Congchao Wang, JianHang Chen +3
The paper proposes the Critic Experience Bank, a training-free framework that lets large language model agents estimate confidence for each action by storing and retrieving past st…
ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing
Yaopei Zeng, Congchao Wang, Blake JianHang Chen +1
The paper proposes two methods—a attention‑based probe and a KL‑regularized LoRA probe (ReLope)—to improve routing decisions in multimodal large language models by extracting more…
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…
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…