14 papers
Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling
Xinmu Ge, Zizhuo Zhang, Yu Huang +9
On-policy distillation (OPD) has emerged as a promising post-training technique for enhancing LLM reasoning. It is commonly believed to enable the student model to distill knowledg…
Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense
Zhanke Zhou, Bo Han, Xuan Li +3
Graph neural networks (GNNs) are widely deployed on relational data, yet they can leak sensitive or proprietary information about the training graph adjacency, e.g., social ties, t…
RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models
Xiao Feng, Bo Han, Zhanke Zhou +5
Reinforcement learning (RL) shows promise for enhancing LLM agentic reasoning, yet sparse terminal rewards hinder fine-grained optimization. Process reward modeling offers an alter…
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
Jingwei Sun, Jianing Zhu, Jiangchao Yao +2
To enable reliable long-term interaction, LLM agents require a memory system that can faithfully store, efficiently retrieve, and deeply reason over accumulated dialogue history. M…
Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers
Fanqin Zeng, Feng Hong, Geng Yu +6
Diffusion Large Language Models (DLLMs) promise fast parallel generation, yet open-source DLLMs still face a severe quality-speed trade-off: accelerating decoding by revealing mult…
CR^2: Cost-Aware Risk-Controlled Routing for Wireless Device-Edge LLM Inference
Nan Xue, Shengkang Chen, Zhiyong Chen +4
As large language models (LLMs) move from centralized clouds to mobile edge environments, efficient serving must balance latency, energy consumption, and accuracy under constrained…