Skip to content

Author

Weiwen Liu

We have 13 of 60 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

Work Agents: Systems, Capabilities, and Optimization

As foundation models evolve from information generation to digital work execution, agents are increasingly capable of completing complex tasks across tools, applications, and workflows. However, existing research lacks a unified perspective on how agents reliably accomplish delegated work. To address this gap, we prese...

Zi-Shan Xu, En-Jun Du, Mingqi Gao et al. · 0 citations
#software testing Preprint Oct 2026

Evaluating Agentic Capabilities Before Post-Training: An End-to-End Approach

Agentic capabilities are increasingly important for modern LLMs, yet remain difficult to evaluate during pretraining. Existing approaches typically rely on static trajectory-derived tasks or likelihood-based proxies, which are lightweight but provide limited visibility into how base models behave in interactive environ...

Jia-Rui Qin, Jun-Jie Huang, Yun-Jia Xi et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Model What Matters: Decision-Guided Selective World Modeling for Language Agents

Reinforcement learning provides a direct mechanism for optimizing task objectives in large language model-driven agents, but task rewards are typically sparse trajectory-level signals that only evaluate task success, without directly supervising action-conditioned environment transitions, leaving the model with limited...

Mao-Lin Ran, Min-Da Chen, Di Huang et al. · 0 citations
#artificial intelligence Preprint Oct 2026

FleetPilot: Fine-Grained Steering Empowers Real-World LLM Personalization

With the rapid evolution of large language models (LLMs), there is an increasing demand for effective personalization techniques that can adapt model behavior to individual user preferences. Personalized LLMs must infer a user's query-dependent preferences from limited, heterogeneous, and evolving interaction histories...

Kounianhua Du, Jian-Xing Liu, Kang-Ning Zhang et al. · 0 citations
#artificial intelligence Preprint Sep 2026

CodeSkill: Latent Skill Abstraction for Long-Horizon Code Agents

By shifting RL from token-level exploration to experience-level reasoning, CodeSkill improves optimization efficiency and long-horizon behavioral coherence, highlighting the effectiveness of explicit behavioral abstraction for scalable agentic code generation.

Song-Li Wu, Jing-Yi Wang, Zhao-Cheng Du et al. · 0 citations
#artificial intelligence Preprint Sep 2026

MCPGen: Benchmarking LLMs on Executable MCPWorkflow Development

MCPGen is introduced, an executable benchmark for Model Context Protocol (MCP) workflow development that evaluates three diagnostic tasks: workflow reconstruction, tool creation, and backward-compatible workflow extension and evaluates 11 representative LLMs in a single-turn foundation-model setting.

Yingxuan Yang, Jia-Qi Liu, Li-Rui Guan et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agents

The proposed REALM framework models long-term memory as a continual lifecycle by autonomously organizing memories into a heterogeneous cognitive graph, retrieving evidence via adaptively composed graph-search atoms, and continually reconsolidating memories based on retrieval feedback.

Yuan-Yi Song, Yukai Wang, Xin-Bei Ma et al. · 2 citations

From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form Generation

The key observation is that although expert trajectories are scarce, high-quality final artifacts such as literature reviews, analyst reports and legal judgments, are abundant in pre-training data and can be viewed as compressed traces of the evidence-seeking processes that produced them.

Junjie Huang, Jiarui Qin, Di Yin 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.

Mao-Lin Ran, Xiaoyan Lu, Jia-Qi 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 ta...

Shuai Shao, Kangning Zhang, Qingyao Li et al. · 10 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 rew...

Jiaqi Liu, Maolin Ran, Xiaoyan Lu 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.