YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
DPA Research Pipeline — 从 Idea 到代码的完整记录
Decision Point Attention: Strategic Full Attention Routing for Efficient Agent Reasoning with Linear Attention
Target: NeurIPS 2026
这个 Repo 包含什么
1. conversation/ — Claude 对话完整记录
- 4天的研究对话(3/20-3/24)
- 从文献调研 → 20个idea → 选定DPA → 搭建项目的全过程
- 包含: ICL+Long Doc 方向分析、Linear Attention+RAG 10个idea、Agent+ICL+Linear Attention 10个idea
2. agentlab-pipeline/ — AgentLaboratory 自动研究 Pipeline
decision_point_attention.yaml— 研究配置(topic、notes、参数)inference_patched.py— 修改后的推理模块(接入 LLMBox 网关)tools_patched.py— 修改后的工具模块(PDF下载重试)ai_lab_repo_patched.py— 修改后的主程序agentlab_run.log— 运行日志(Literature Review 结果、论文分析)
3. dpa-project/ — DPA 完整项目代码
src/
models/
router.py — Decision Point Router (learned + fixed + supervised loss)
dpa_model.py — DPA 架构 (LinearAttn + FullAttn + Router + Wrapper)
baselines.py — Full Transformer / Pure Linear / Uniform Hybrid
data/
agent_trajectory.py — Agent trajectory 生成器 + decision point 标注
datasets.py — HotpotQA / GSM8K / ToolBench 数据加载
eval/
benchmark.py — 统一评估 (simulate / train / finetune)
metrics.py — FLOPs / latency / KV cache / perplexity
visualize.py — 出版级图表生成
configs/ — 本地simulation + Merlin 8xH100 训练配置
scripts/ — 运行脚本
data/ — 2000条标注 agent trajectories
results/ — Simulation 结果 (13 model variants)
4. figures/ — 生成的论文图表
accuracy_vs_flops.pdf— Quality vs Compute tradeoffratio_ablation.pdf— Decision Point Ratio 消融实验trajectory_analysis.pdf— Agent Trajectory 中 decision point 分布
复现步骤
# 1. 本地运行 simulation (无需 GPU)
cd dpa-project
pip install -r requirements.txt
python src/data/agent_trajectory.py # 生成数据
python src/eval/benchmark.py --mode simulate # 跑 simulation
python src/eval/visualize.py results/simulation_results.json # 生成图表
# 2. 用 AgentLaboratory 自动研究 (需要 LLM API)
cd agentlab-pipeline
# 先 clone AgentLaboratory:
# git clone https://github.com/SamuelSchmidgall/AgentLaboratory.git
# 复制 patched 文件覆盖原文件, 然后:
python ai_lab_repo_patched.py --yaml-location decision_point_attention.yaml
# 3. 在 Merlin 上训练 (8xH100)
cd dpa-project && bash scripts/run_dpa.sh
Key Findings from AgentLab Literature Review
AgentLaboratory 自动分析了以下论文与 DPA 的关联:
- Routing Transformer (Roy et al., 2020) — Content-based sparse routing 先驱,证明 selective global attention 优于 uniform sparsity
- HAG (Roffo et al., 2024) — Hard gating + gradient routing 训练策略,可用于 DPA router 训练
LLMBox 网关配置 (字节内部免费)
AgentLaboratory 通过 LLMBox 网关调用 LLM, 无需 OpenAI API Key:
- Base URL:
https://llmbox.bytedance.net/v1 - 在
inference_patched.py中添加了llmbox/模型前缀支持 - 修复了 LLMBox 返回 list (而非 string) 的兼容性问题
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support