12 citations · 23 across the 19 of their papers we have counts for
8 papers · 1 filter
ReFlow: Replay-Driven Decoupling for Efficient RL Post-Training
Yukun Tian, Junwei Su, Haofeng Xu +6
Reinforcement learning (RL) has been a critical paradigm for improving large language model (LLM) reasoning and agentic capabilities, but its efficiency remains a major bottleneck.…
Reward-Aligned Reweighting for On-Policy Distillation
Haofeng Xu, Junwei Su, Lansong Diao +2
On-policy distillation (OPD) trains a student language model with dense feedback from a stronger teacher on student-generated trajectories. Yet standard OPD weights token-level dis…
Structuring Relations Among Learning Paradigms via Protocol--Objective--Resource Reductions
Junwei Su, Changjie Wang, Dongyang Chang
Modern machine learning spans supervised, transfer, continual, meta-learning, and related regimes that often reuse the same hypothesis classes, architectures, and optimizers but di…
Structuring Semantic Embeddings for Principle Evaluation: A Prototype-Guided Contrastive Learning Approach
Che Shen, Junwei Su, Lingpeng Kong +1
Reliable post-hoc evaluation asks whether already generated text satisfies a target criterion after generation. In this paper we study a focused frozen-embedding setting using prin…
GeomHerd: A Forward-looking Herding Quantification via Ricci Flow Geometry on Agent Interactive Simulations
Lake Yang, Junwei Su, Jingfeng Zeng +5
Herding -- where agents align their behaviors and act collectively -- is a central driver of market fragility and systemic risk. Existing approaches to quantify herding rely on pri…
GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control
Haofeng Xu, Junwei Su, Yukun Tian +3
Asynchronous execution is essential for scaling reinforcement learning (RL) to modern large model workloads, including large language models and AI agents, but it can fundamentally…
When Do Multi-Agent Systems Outperform? Analysing the Learning Efficiency of Agentic Systems
Junwei Su, Chuan Wu
Reinforcement Learning (RL) has emerged as a crucial method for training or fine-tuning large language models (LLMs), enabling adaptive, task-specific optimizations through interac…
ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation
Jingqi Zhou, Sheng Wang, Dezhao Deng +9
LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution. Such rigidity forces a trade-off between do…