20 papers
MemWM: Memory-Augmented Text-Based World Model
Yujun Wang, Tao Zhang, Jinhe Bi +9
World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent next-state predictions can sti…
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
Aniri, Jinhe Bi, Peng Liao +5
On-Policy Self-Distillation (OPSD) has become a standard post-training approach for improving visual reasoning in multimodal large language models (MLLMs). Existing methods draw pr…
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Jinhe Bi, Chennan Zhou, Zengjie Jin +10
On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories…
MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
Zefeng Wang, Minxi Yan, Jinhe Bi +3
Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further extend this capability. Howe…
Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence
Xuanle Zhao, Qiushi Sun, Jingyu Xiao +16
While Large Language Models (LLMs) have substantially advanced text-to-code synthesis, many real programming tasks specify intent through visual artifacts such as screenshots, char…
EchoRL: Reinforcement Learning via Rollout Echoing
Jinhe Bi, Aniri, Minglai Yang +9
Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models. However, as training proceed…