PhD candidate @ Nankai University, College of Computer Science | Research on retrieval-augmented LLMs, knowledge-conflict control, long-context memory, and the agent-harness engineering substrate that makes LLM agents finish long-horizon tasks reliably.
| Area | Project | Stars | Notes |
|---|---|---|---|
| RAG / knowledge-conflict control | Swin-VIB | 1 | Source code for the AAAI 2026 paper Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Robust Response Generation in the Wild. |
| Multi-view representation | DistilMVC | 4 | Source code for the TNNLS 2024 paper Towards Generalized Multi-stage Clustering: Multi-view Self-distillation. |
| Research feed | MyArxiv | new | Personal arXiv tracking and digest setup. |
| Project | PR | What I Did |
|---|---|---|
| openclaw (379k★) | #78288 | Show target node name in exec-tool transparency messages so multi-agent traces stay readable when several agents share an exec channel. |
- All-Hands-AI/OpenHands — Condenser subsystem contributions (long-context compression & policy).
- bytedance/deer-flow — memory-module PRs.
Retrieval-augmented generation under context distortion · knowledge-conflict control · learnable long-context compression · agent context-management policy evaluation.
南开大学计算机学院在读博士 | 研究方向：检索增强大模型、知识冲突控制、长上下文记忆，以及让 LLM Agent 稳定完成长跨度任务的 agent harness 工程底座。
| 方向 | 项目 | Stars | 简介 |
|---|---|---|---|
| RAG / 知识冲突控制 | Swin-VIB | 1 | AAAI 2026 论文《Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Robust Response Generation in the Wild》源码实现。 |
| 多视图表征 | DistilMVC | 4 | TNNLS 2024 论文《Towards Generalized Multi-stage Clustering: Multi-view Self-distillation》源码实现。 |
| 研究追踪 | MyArxiv | new | 个人 arXiv 跟踪与摘要工具。 |
| 项目 | PR | 修了啥 |
|---|---|---|
| openclaw (379k★) | #78288 | 在 exec 工具的透传消息中展示目标节点名，让多个 agent 共享 exec 通道时的执行轨迹依然可读。 |
- bytedance/deer-flow —— 向 memory 模块提交 PR。
检索增强生成下的上下文失真 · 知识冲突控制 · 可学习的长上下文压缩 · Agent 上下文管理策略评测。