[P6] RL-VLA$^3$: Reinforcement Learning VLA Accelerating via Full Asynchronism

Haoran Sun*, Yongjian Guo*, Zhong Guan*, Shuai Di, Xiaodong Bai, Jing Long, Tianyun Zhao, Mingxi Luo, Hongke Zhao, Likang Wu, Xiaotie Deng, Xu Chu, Xi Xiao, Sheng Wen, Yicheng Gong, Junwu Xiong

Presented at ICLR 2026 Workshop on Scaling Post-training for LLMs

• Efficient asynchronous reinforcement learning framework for Vision-Language-Action models.

[P5] LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots

Haoran Sun, Xinrui Song, Xinyu Zhang, Zhaohua Chen, Xu Chu, Zhilin Zhang, Chuan Yu, Jian Xu, Bo Zheng, Xiaotie Deng

• Novel RAG-based approach for advertising auction in generative chatbot environments.

[P4] NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models

Wen Huang*, Haoran Sun*, Yongjian Guo*, Yunxuan Ma, Haoran Li, Jing Long, Zhouying Mo, Zhong Guan, Yucheng Guo, Shuai Di, Junwu Xiong

• Novel timestep scheduling method for world models in embodied AI.

[P3] Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction

Zhong Guan*, Yongjian Guo*, Haoran Sun*, Wen Huang, Shuai Di, Junwu Xiong, Likang Wu, Hongke Zhao

• Analysis and solution for semantic mismatch in asynchronous agentic reinforcement learning.

[P2] Thousand-GPU Large-Scale Training and Optimization Recipe for AI-Native Cloud Embodied Intelligence Infrastructure

JDT AI Infra Team

• Large-scale distributed training recipe for embodied intelligence systems.

[P1] Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers

Haoran Sun, Yusen Wu, Peng Wang, Wei Chen, Yukun Cheng, Xiaotie Deng, Xu Chu

• Extended version of our IJCAI 2025 survey with expanded taxonomy and new frontiers.

[C9] Enhancing Affine Maximizer Auctions with Correlation-Aware Payment

Haoran Sun, Xuanzhi Xia, Xu Chu, Xiaotie Deng

• Proposed correlation-aware affine maximizer auctions for correlated bidders.

[C8] Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective

Siwei Wang$^*$, Yifei Shen$^*$, Haoran Sun$^*$, Shi Feng$^*$, Shang-Hua Teng, Li Dong, Yaru Hao, Wei Chen

• Theoretical analysis of RL methods for LLM planning, revealing benefits and pitfalls.

[C7] Scalable Virtual Valuations Combinatorial Auction Design by Combining Zeroth-Order and First-Order Optimization Methods

Zhijian Duan$^*$, Haoran Sun$^*$, Yichong Xia, Siqiang Wang, Zhilin Zhang, Chuan Yu, Jian Xu, Xiaotie Deng

• Novel combinatorial auction design combining zeroth-order and first-order optimization.

[C6] Mechanism Design for LLM Fine-tuning with Multiple Reward Models

Haoran Sun, Yurong Chen, Siwei Wang, Wei Chen, Xiaotie Deng

• Mechanism design framework for LLM fine-tuning with multiple reward models.

[C5] Game Theory Meets Large Language Models: A Systematic Survey

Haoran Sun, Yusen Wu, Yukun Cheng, Xu Chu

• Comprehensive survey on the intersection of game theory and LLMs.

[C4] Amulet: Realignment during Test Time for Personalized PreferenceAadaptation of LLMs

Zhaowei Zhang*, Fengshuo Bai*, Qizhi Chen, Chengdong Ma, Mingzhi Wang, Haoran Sun, Zilong Zheng, Yaodong Yang

[C3] ALPINE: Unveiling The Planning Capability of Autoregressive Learning in Language Models

Siwei Wang*, Yifei Shen*, Shi Feng, Haoran Sun, Shang-Hua Teng, Wei Chen

• Empirical study of planning-like behavior emerging from vanilla autoregressive LM training objectives.

[C2] A Scalable Neural Network for DSIC Affine Maximizer Auction Design

Zhijian Duan, Haoran Sun, Yurong Chen, Xiaotie Deng

• Neural network approach for designing affine maximizer auctions.

[C1] Coordinated Dynamic Bidding in Repeated Second-Price Auctions with Budgets

Yurong Chen*, Qian Wang*, Zhijian Duan, Haoran Sun, Zhaohua Chen, Xiang Yan, Xiaotie Deng