36 posts in total
2026
Reading Notes of DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference
Reading Notes of SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
Reading Notes of SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning
Simulation Modeling
1. Discrete Event Simulation
2. Review of Probability and Statistics
3. Random Number Generation
4. Generating Random Variates
5. Selecting Input Probability Distributions
Reading Notes of CacheCraft: Discovering KV Cache Eviction Policies via LLM-Guided Program Evolution