Skip to content

Author

Pengyuan Wang

We have 6 of 14 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors

The Alpha-Stabler framework is proposed, a plug-and-play framework with a Predictor that monitors principal-subspace intrusion for early collapse warnings, and a Controller that removes the principal-subspace component of activation gradients during backpropagation while preserving the orthogonal complement.

Yu-Chen Cai, Ding Cao, Qi-Xiang Yin et al. · 1 citation
Book Open access Aug 2026

Constructive Specification for Plug-and-Play Learnware Agents

This work operationalizes constructive specification with constructive specification, which builds hierarchical capability representations from limited profiling over diverse benchmarks, using an optimism-guided profiler that prioritizes informative regions and prunes low-utility areas with guarantees, and enables plug...

Jian-Dong Liu, Zi-Chen Zhao, Hao Sun et al. · 4 citations · ⚡1
2025

Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function

This work proposes MAFIS, a novel method that addresses limitations for both online and offline MAIL settings by building upon the single-agent IQ-Learn framework and introducing the value decomposition network to factorize the imitation objective at agent level, thus enabling scalable training for multi-agent systems.

Yichen Li, Zhongxiang Ling, Tao Jiang et al. · 3 citations
Preprint Jul 2026

Efficient Test-Time Optimization for Multi-Agent Proof Autoformalization

ToMap is introduced, a multi-agent framework that structures proof autoformalization as a Decomposer-Formalizer-Prover pipeline with efficient test-time optimization guided by formal verification and semantic rubrics for proof quality.

Tian-Shuo Liu, Shiyuan Zhang, Zijie Geng et al. · 2 citations · ⚡1
#natural language process... Preprint Aug 2026

Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms

This work compares three fusion paradigms by the artefacts they reuse and suggests that Merge when experts already exist and cheap fusion is paramount; Mix RL when training a unified model without experts, with domain proportions adjusted for cross-domain transfer; and MOPD when preserving domain-specific gains matters...

Sicheng Wu, Kai Yang, Yu-Chen Cai et al. · 5 citations · ⚡1
Book Open access Aug 2026

Constructive Specification for Plug-and-Play Learnware Agents

This work operationalizes constructive specification with constructive specification, which builds hierarchical capability representations from limited profiling over diverse benchmarks, using an optimism-guided profiler that prioritizes informative regions and prunes low-utility areas with guarantees, and enables plug...

Jian-Dong Liu, Zi-Chen Zhao, Haodong Sun et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.