2026
-
Pi Agent：Containerization 与 Compaction
TLDR: Coding agents need sandboxed execution, context compaction, and continuation mechanics so long-running work can survive safely across many tool calls.
-
MAS Conference Papers：近期多智能体系统论文阅读清单
TLDR: This page is a ranked reading shortlist for recent MAS papers, prioritizing collaboration structure, topology design, runtime efficiency, and verification.
-
Beyond Individual Intelligence：LLM-based Multi-Agent Systems 的 LIFE 框架
TLDR: The LIFE survey reframes LLM multi-agent systems as a lifecycle: build individual capability, integrate collaboration, attribute failures, then evolve the system.
-
《自私的基因》第11章：Meme，新的复制因子
TLDR: Memes extend the book from genes to culture: ideas, habits, and symbols can also copy, compete, mutate, and reshape human behavior.
-
《自私的基因》第12章：好人终有好报
TLDR: Repeated interaction changes the logic of selfishness, making cooperation viable when strategies can be nice, retaliatory, forgiving, and non-envious.
-
Sutton RL Chapter 6：Temporal-Difference Learning
TLDR: TD learning updates from partial experience by bootstrapping current value estimates, combining Monte Carlo sampling with dynamic-programming-style updates.
-
Sutton RL Chapter 5：Monte Carlo Methods
TLDR: Monte Carlo methods learn value from complete sampled episodes, trading model-free simplicity for delayed updates and return variance.
-
Sutton RL Day 2：Multi-Armed Bandits
TLDR: Multi-armed bandits isolate the exploration/exploitation problem by removing state transitions and making action-value estimation the center.