AI agents win at Slay the Spire 2 after researchers replace growing chat logs with structured memory
The AgenticSTS project replaces the ever-growing chat log of AI agents with five separate memory layers. Tested on the card game Slay the Spire 2, the prompt stays at around 5,000 tokens instead of ballooning past 500,000. The agent wins 6 out of 10 games, while competing agents don't win any.<br /> The article AI agents win at Slay the Spire 2 after researchers replace growing chat logs with structured memory appeared first on The Decoder. [...]
Rating
Innovation
Pricing
Technology
Usability
We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.
Slay the Spire 2, Scott Pilgrim EX and other new indie games worth checking out
Welcome to our latest roundup of what's going on in the indie game space. We've got a lot of new and upcoming games to highlight this week, and those are on top of all of our coverage of the [...]
A 0.12% parameter add-on gives AI agents the working memory RAG can't
AI agents forget. Every time a coding assistant loses track of a debugging thread, or a data analysis agent re-ingests the same context it already processed, the team pays in latency, token costs, and [...]
New memory framework builds AI agents that can handle the real world's unpredictability
Researchers at the University of Illinois Urbana-Champaign and Google Cloud AI Research have developed a framework that enables large language model (LLM) agents to organize their experiences into a m [...]
Google PM open-sources Always On Memory Agent, ditching vector databases for LLM-driven persistent memory
Google senior AI product manager Shubham Saboo has turned one of the thorniest problems in agent design into an open-source engineering exercise: persistent memory.This week, he published an open-sour [...]
98% of market researchers use AI daily, but 4 in 10 say it makes errors — revealing a major trust problem
Market researchers have embraced artificial intelligence at a staggering pace, with 98% of professionals now incorporating AI tools into their work and 72% using them daily or more frequently, accordi [...]
DeepSeek’s conditional memory fixes silent LLM waste: GPU cycles lost to static lookups
When an enterprise LLM retrieves a product name, technical specification, or standard contract clause, it's using expensive GPU computation designed for complex reasoning — just to access stati [...]
Shadow mode, drift alerts and audit logs: Inside the modern audit loop
Traditional software governance often uses static compliance checklists, quarterly audits and after-the-fact reviews. But this method can't keep up with AI systems that change in real time. A mac [...]