activity
20242026
most citedBeyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS

3 citations · 6 across the 15 of their papers we have counts for

collaborators

16 papers

cs.CV2026

Decoupled Visual Processing: Efficient Multimodal Adaptation via Modality-Specific Transformer Substitution

Mingkuan Feng, Zhengqi Wen, Jianhua Tao

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual understanding within a unified transformer architecture. Howeve…

cs.CL2026

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Jinyang Wu, Shuo Yang, Zhengxi Lu +8

Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based rein…

cs.MA2026

TACO: Tool-Augmented Credit Optimization for Agentic Tool Use

Mingkuan Feng, Jinyang Wu, Hao Gu +5

Agentic multimodal models perform diverse operations on an image via code and reason over the returned view, an effective paradigm for fine-grained visual question answering. Howev…

cs.CL2026

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Shuo Yang, Jinyang Wu, Zhengxi Lu +8

Outcome-based reinforcement learning provides a stable optimization backbone for language agents, but its sparse trajectory-level rewards provide little guidance on which intermedi…

cs.LG2026

Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles

Jinyang Wu, Guocheng Zhai, Ruihan Jin +7

The proliferation of large language models (LLMs) and modular skills has endowed autonomous agents with increasingly powerful capabilities. Existing frameworks typically rely on mo…

cs.LG2026

Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning

Jinyang Wu, Shuo Yang, Changpeng Yang +4

Reinforcement learning has empowered large language models to act as intelligent agents, yet training them for long-horizon tasks remains challenging due to the scarcity of high-qu…