Skip to content

Author

Qing-Peng Cai

We have 9 of 18 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.

Preprint Oct 2026

Skill-V: Verifiable Self-Evolving Skill Library for Interactive Agents

Skill-V is introduced, a verifiable self-evolving skill library representing skills as versioned, falsifiable contracts that link semantic intent to observable behavioral criteria, and environment outcomes are used to drive library evolution.

Jie Ma, Zhi-Peng Qian, Yu-Fei Ma et al. · 0 citations
Sep 2026

SRPO: Setwise Relative Policy Optimization for Multi-Agent Systems

Multi-agent systems enable complex reasoning and tool use by coordinating agents that divide roles and refine candidate solutions. Existing methods typically update individual agent responses or treat a complete trajectory as one training example. However, these methods may produce misleading policy updates because the...

Sheng-Tian Yang, Zi-Yun Xiong, Yu Li et al. · 0 citations
Book Open access Aug 2026

Generative Auto-Bidding in Large-Scale Auctions via Diffusion Completer-Aligner

This work proposes a Causal auto-Bidding method based on a Diffusion completer-aligner framework, termed CBD, which achieves superior performance on large-scale auto-bidding benchmarks, but also delivers significant improvements on an online advertising platform, including a 2.0% increase in target cost.

Ye-Wen Li, Jingtong Gao, Peng Jiang et al. · 0 citations

Dr. Free: You Don't Need Difficulty Rewards for Self-Evolving Search Agents

This paper introduces \methodname, the first self-evolving search framework that eliminates difficulty-based proposer rewards and directly optimizes for evidence necessity relative to shortcut contexts, and shows that Dr. Free outperforms prior data-free search agents and the supervised baseline.

Zhi-Peng Qian, Zi-Han Liang, Yu-Fei Ma et al. · 0 citations
#artificial intelligence Preprint Sep 2026

OneBid: A Unified Auto-Bidding Foundation Model for Diverse oCPX Advertising Scenarios

OneBid is presented, a unified auto-bidding foundation model that learns a reusable backbone from heterogeneous oCPX logs and adapts it to scenario-specific deployments via offline post-training, and designs a sequence-level Mixture-of-Experts architecture to absorb distributional heterogeneity.

Ye-Wen Li, Peng Jiang, Yi-Tian Li et al. · 0 citations
#artificial intelligence Preprint Sep 2026

SRPO: Setwise Relative Policy Optimization for Multi-Agent LLMs

SRPO (Setwise Relative Policy Optimization), which treats the active set the minimal set of outputs consumed by one transition, as one multi-agent action, and unifies division of labor and joint co-evolution as actions with different set sizes.

Sheng-Tian Yang, Zi-Yun Xiong, Yu Li et al. · 4 citations
#artificial intelligence Preprint Sep 2026

AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories

AgentBrew is proposed, an offline training framework that learns effective tool-use policies from a single batch of raw interaction trajectories, without task verifiers or iterative on-policy rollouts, and demonstrates that fine-grained offline learning can recover useful supervision from raw trajectories that filterin...

Zhiyi Lyu, Ye-Wen Li, Long-Tao Zheng et al. · 2 citations
#machine learning Preprint Aug 2026

PRQ-KMeans: Projection Residual Quantization for Semantic ID Tokenization

This work proposes PRQ-KMeans, which removes the global-mean component, refines centroids with Top-k similarity-weighted updates, and replaces full-codeword subtraction with a projection residual that removes each representation's selected-centroid component.

Yunxiao Luo, Siyuan Wang, Ben Chen et al. · 0 citations
Book Open access Aug 2026

Hierarchical Residual Policy Optimization for Generative Recommendations

Hierarchical Residual Policy Optimization (HRPO), a post-training framework that converts item-level outcomes into dense, token-aligned learning signals for conservative token-wise improvement, is proposed.

Kaifeng Guo, Yiming Yang, Jingtong Gao et al. · 0 citations

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