Skip to content

Author

Weinan Zhang

6 papers indexed here

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 Aug 2026

What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents

LLM agents increasingly rely on generated interaction data to learn how to interact with external environments. Agentic data generation must maintain consistency among environments, tasks, interactions, and success signals while producing experience that is useful rather than merely abundant. Existing work spans many agent domains, but domain-centered organization and heterogeneous evaluation often obscure common generation mechanisms and conflate candidate construction with verification and selection. This work develops a two-level framework for the field. First, we represent agentic data as a common factorized object $(E,q,\tau,v)$, comprising an environment specification, task signal, interaction realization, and optional verifier. We organize generation paradigms by their primary anchor and dependency structure. Second, we formulate generation as constrained distribution design through the Accuracy-Complexity-divErsity (ACE) lens. Accuracy establishes the feasible support of grounded and internally consistent data. Within this support, Complexity places learning mass relative to the capability of a declared learner and execution configuration, while divErsity controls coverage and redundancy of data. Using this framework, we explore how prior work verifies generated experience, constructs and calibrates difficulty, and expands behavioral coverage. The literature reveals a shift toward execution-grounded accuracy, learner-relative complexity, and diversity beyond surface variation or dataset size. We further discuss broader directions and emerging trends in agentic data generation through the ACE lens, including their implications for scaling, data sources, training regimes and adaptive learning. Overall, the central challenge is not simply to generate more data, but to continually allocate valid, informative, and non-redundant experience as agents and environments evolve.

Xingshan Zeng, Zishan Xu, Bo-Ju Zhang et al. · 0 citations
Preprint Aug 2026

SAGE: Self-Evolving Storyboard Skills via Attribution-Guided Rule Evolution

This work presents SAGE (Skill with Attribution-Guided Evolution), a deployed framework that learns, attributes, evolves, and routes directing knowledge from expert demonstrations, and releases PROSE, the first public dataset pairing screenplays with storyboards by professional directors across 68 episodes.

Maolin Ran, Xiaoyan Lu, Jiaqi Liu et al. · 0 citations
Preprint Jul 2026

IssueExec: A Test-Driven Approach for Localizing Software Engineering Issues

The proposed IssueExec bridges the semantic gap through domain-knowledge-enhanced test representations and filters noise via hierarchical trace analysis, which bridges the semantic gap through domain-knowledge-enhanced test representations and filters noise via hierarchical trace analysis.

Jiawei Liu, Yun Lin, Chenyan Liu et al. · 0 citations
Preprint Aug 2026

Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories

This work introduces Harness-R1, the first method, to the authors' knowledge, that makes failure-conditioned, lifecycle-wide editing of an existing executable runtime a learned capability, and post-trains a dedicated harness engineer with online reinforcement learning so that its edits are optimized for the realized task success they produce.

Shuai Shao, Kangning Zhang, Qingyao Li et al. · 6 citations · ⚡2
#small language model Preprint Aug 2026

SEAM: Shot Entity-Attribute Memory for Consistent Short-Drama Generation at Scale

A training-free, model-agnostic memory graph that repairs continuity entirely at the prompt-text layer by extracting a multi-dimensional state for every shot, retrieving only causally prior context over the resulting graph, filtering it selectively, and injecting the surviving constraints by natural-language prompt rewriting.

Jiaqi Liu, Maolin Ran, Xiaoyan Lu et al. · 0 citations