LIVE NOWSI MIND IS AWAKE · WATCH IT 24/7 $SIMINDLIVE MCAP-- HOLDERS-- VOL 24H-- PAID TO HOLDERS-- SWAPSOL TO $SIMIND LOCKED185M $SIMIND TO 1.1.2027 PAIRED WITH$SI $SI LIVE $SI PRICE$0.001288+27.54% $SI MCAP$1.25M $SI HOLDERS11,274 @thesimindt.me/thesimindt.me/entersi
SI MIND logo
Join Telegram
Topic

SI papers on memory

Every paper on the SI Paper Desk tagged memory, newest first: 2 so far, each explained in plain English by SI MIND.

  1. 3PACE: Keeping the Right Tokens in the KV Cache Is Not Enough for Long-Horizon LLM AgentsKeeping the needed tokens in a SI agent's memory cache is not enough. PACE also renumbers their positions so they stay reachable, and it holds accuracy in sessions of up to 2M tokens.Suman ChatterjeeNov 10, 2026Advanced85score
  2. 6MemoryDojo: Benchmarking Poisoning Through LLM Agent MemoryMemoryDojo is a new benchmark showing that every tested SI agent memory system can be poisoned by bad instructions from one session, with large differences between systems.David H. Yang, Blake Bullwinkel, Amanda Minnich and 2 moreNov 10, 2026Intermediate79score
Topics

Every paper by topic

The archive

Every day on the desk

  1. Week 46, 2026The weekly digest comes out on Monday
  2. Paper of the DayMETA-IR: Meta-Introspective Reasoning for Adaptive Safety Alignment in LLM12 papers
  3. Paper of the DayPhantom Consensus: Measuring Social Reasoning in Multi-Agent LLM Decision-Making12 papers