Jun Chen

VenusRL: A Fully Disaggregated Agentic RL System with Priority Scheduling and Scalable Interaction

Agentic Reinforcement Learning (RL) trains LLM agents through multi-turn interactions with external tool environments. Its multi-turn nature exposes two system-level bottlenecks unaddressed by existing agentic RL frameworks. First, end-to-end training throughput is constrained by the slowest trajectories to complete, y...

Reproducing UI contexts described in app reviews with large language models

Semantic Projection for Continual Self-Evolution of Language Agents

Semantic-Scope Projected Evolution (SSPE) is introduced, which transfers the functional principle of gradient projection from parameter space to behavior space and establishes semantic projection as a promising principle for stable and adaptive self evolution of language agents.

Dual-Process Atomic Skill Learning: Decoupling Semantic Reasoning and Real-Time Control

This work proposes Dual-Process Atomic Skill Learning (DASL), a novel asynchronous hierarchical imitation learning framework that decouples slow semantic reasoning from fast, real-time motion control and mitigates the skill codebook interference problem common in joint training paradigms.

GTA-RAG: Graph-Trajectory-Augmented Reinforcement Learning for Multi-Turn Retrieval-Augmented Reasoning

This work presents \textsc{GTA-RAG}, a graph-trajectory-augmented RL framework for multi-turn retrieval-augmented reasoning that consistently outperforms RL-based RAG baselines with both Qwen2.5-3B and Qwen2.5-7B backbones, while substantially improving evidence-chain coverage.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models

Oyster-II is proposed, a reinforcement learning (RL)-based constructive safety alignment framework that adopts a Zero-RL paradigm combined with a multi-stage reinforcement learning strategy that comprehensively surpasses both Qwen3-14B and its predecessor Oyster-I on safety dimensions.