📚 Reading List

A curated collection of papers I’m reading, planning to read, or have completed. This table helps me track my progress and whether I’ve created detailed cards for each paper.

Status	Paper Title	Card Created	Notes
Completed	BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining	✅ Yes	High priority - synthetic data scaling
Reading	Memento: Fine-tuning LLM Agents without Fine-tuning LLMs	✅ Yes	Continual learning for agents
Completed	PickLLM: Context-Aware RL-Assisted Large Language Model Routing	✅ Yes	RL for LLM selection - interesting approach
Completed	Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning	✅ Yes	Multi-step routing with RL - excellent framework
Reading	Deep Graph Anomaly Detection: A Survey and New Perspectives	✅ Yes	Comprehensive survey - good reference
Completed	Deep Think with Confidence	✅ Yes	Confidence-based reasoning filtering - practical
Not Started	gpt-oss-120b & gpt-oss-20b Model Card	❌ No	Model card for new open-weight reasoning models from OpenAI with agentic capabilities.
Not Started	R-Zero: Self-Evolving Reasoning LLM from Zero Data	❌ No	Fully autonomous framework where Challenger/Solver models co-evolve to generate their own training curriculum from scratch.
Not Started	Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning	❌ No	An agentic GraphRAG that models retrieval as a multi-turn interaction and optimizes it with end-to-end RL.
Not Started	A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence	❌ No	The first systematic survey of self-evolving agents, organized by what, when, and how agents evolve.