Skip to content

Author

Zhongwei Xie

We have 12 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.

Preprint Oct 2026

CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents

This work presents CoworkEnv, a capability-guided framework for synthesizing executable training environments for AI coworkers, and compares RL training dynamics across configurations that vary reward processing and credit assignment.

Zhong-Wei Xie, Yi-Ming Du, Jiaxin Bai et al. · 0 citations
#artificial intelligence Preprint Nov 2026

OGDA: Ontology-Grounded Data Agents for Reliable Analysis over Heterogeneous Data Lakes

Full-pipeline data analysis over real-world data lakes requires LLM agents to locate and integrate information across large collections of tables with different schemas. Existing data agents follow task-specific exploration, which exhausts the context window in massive lakes. As the context fills, the agent's reasoning...

Bo-Yi Zhang, Hong Ting Tsang, Yi-Sen Gao et al. · 0 citations
Preprint Oct 2026

MOSAIC: An Omni-Modal Benchmark for Long-Term Memory and Cross-Modal Reasoning in Conversational Agents

Omni-modal assistants must remember not only what users say, but also what they show and convey. Existing long-term memory benchmarks are mostly text-and-image or report a single end-to-end score, so they cannot locate whether evidence is lost when it is represented, retrieved, delivered, or read. We introduce MOSAIC,...

Hong Ting Tsang, Bo-Yi Zhang, Haoyu Huang et al. · 0 citations
#artificial intelligence Preprint Oct 2026

JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making

Repeated event forecasting requires extracting predictive signals from noisy evidence and evaluating their value across successive decisions. We introduce JockeyBench, a benchmark and evaluation protocol that studies this problem through historical Japanese horse racing. The protocol combines time-gated evidence, price...

Zhong-Wei Xie, Xing-Su Li, Jing Yu et al. · 0 citations
#artificial intelligence Preprint Oct 2026

RadixFlow: Filling Execution Bubbles in Prefix-Cached Hybrid LLM Serving

Prefix reuse improves LLM inference by sharing the KV cache of common prompt prefixes. This helps only if the scheduler can execute a matched branch in the current worker round. Schedulers assume that a matched prefix is ready, which holds for full attention but fails for hybrid LLMs. There, a branch (the consumer) may...

Hui-Hao Jing, Wen-Bin Hu, Shao-Jin Chen et al. · 0 citations
#artificial intelligence Review Oct 2026

Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization

A benchmark that contrasts authorization evidence for the same operation in its language track is introduced, which combines expert-annotated natural-language scenarios with executed and verified operations, plus externally sourced native-policy requests.

Hui-Hao Jing, Shao-Jin Chen, Wen-Bin Hu et al. · 0 citations
#artificial intelligence Preprint Oct 2026

SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition

Long-horizon agents must complete workflows in which later activities depend on earlier outputs and changes to shared state. A key challenge for evaluation is to expand task requirements and their dependencies while keeping tasks executable and outcomes verifiable. We introduce SkillHorizon, a benchmark that constructs...

Yuxuan Liu, Zhao-Chen Su, Hang-Yu Guo et al. · 0 citations

SoFT: Soft Targets for Generalizable LLM Fine-Tuning

This work proposes soft-target fine-tuning (SoFT) to balance learning from teacher demonstrations with retaining the Base model's existing capabilities, with improvements in both in-distribution capability acquisition and out-of-distribution generalization.

Hui-Hao Jing, Wen-Bin Hu, Shao-Jin Chen et al. · 1 citation

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision

Evaluated across three main benchmarks, two domain-specific studies, and six LLMs, SkillRevise substantially outperforms one-shot baselines, and the revised skills transfer across both executors and task environments, suggesting that SkillRevise captures reusable procedural knowledge beyond any single executor.

Yuxuan Liu, Zhao-Chen Su, Lin Xie et al. · 17 citations
Preprint Jul 2026

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds

Overall, persistent skill self-evolution is better understood as sparse, validation-filtered search with model- and benchmark-dependent returns, rather than steady improvement from additional rounds.

Yuxuan Liu, Zhaochen Su, Yuhao Zhang et al. · 2 citations
Review Jul 2026

Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions

This survey treats isolation as a first-class principle for LLM-agent system safety, and organizes the literature with a boundary-centric taxonomy of five boundaries: user-agent, agent-tool, agent-execution, agent-agent, and system-environment.

Huihao Jing, Wenbin Hu, Shaojin Chen 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.