Editorial illustration for COALA paper defines agent memory types: procedural rules and semantic facts
COALA: AI Agents Get Smarter with Advanced Memory Types
COALA paper defines agent memory types: procedural rules and semantic facts
The AI industry is obsessed with memory. It's treated as a mystical new organ, demanding custom architecture and bespoke brain-lobes. Then a formal academic document, the COALA paper, dropped a deflatingly simple taxonomy.
Agent memory, it states, is just three things: rules, facts, and records. LangChain's engineers saw that tidy list. They skipped the implied homework.
The COALA paper defines memory for agents in three categories: - Procedural: the set of rules that can be applied to working memory to determine the agent's behavior - Semantic: facts about the world - Episodic: sequences of the agent's past behavior How we built our memory system We represent memory in Agent Builder as a set of files. This is an intentional choice to take advantage of the fact that models are good at using filesystems. In this way, we could easily let the agent read and modify its memory without having to give it specialized tools - we just give it access to the filesystem!
So their solution wasn't a specialized module. It was a folder. Pragmatism verging on dismissal.
Large language models already parse text and navigate directories. Why force a novel API? In Agent Builder, `rules.txt` holds procedures.
`facts.txt` keeps semantics. `episodic_log.txt` gets the logs. Remembering is just opening a document, scanning it, maybe appending a line.
This rejects the core premise. It implies the real bottleneck isn't memory design, but our reluctance to use the boring, universal tools we already have. Sometimes a filesystem is just a filesystem.
Sometimes, it's the entire architecture.
Related Reading
Research & Benchmarks Google's FACTS benchmark shows 70% factuality ceiling across four tests
Research & Benchmarks Databricks finds multi-step agents beat single-turn RAG by 21% to 38% on STaRK
Research & Benchmarks Nvidia's DLSS 4.5 beta adds 6x Multi Frame Generation for RTX 50 GPUs
From Archives Google DeepMind's Decoupled DiLoCo hits 88% goodput despite hardware failures
From Archives Agent observability powers production evaluation through trace analysis
Common Questions Answered
What are the three memory categories defined in the COALA paper for autonomous agents?
The COALA paper defines three memory categories for agents: procedural memory (rules for behavior), semantic memory (facts about the world), and episodic memory (sequences of past behavior). These memory types provide different mechanisms for understanding and shaping an agent's actions and knowledge.
How does Agent Builder represent memory in its system?
Agent Builder represents memory as a set of files, deliberately leveraging the ability of AI models to work effectively with filesystems. This approach allows for easy querying, updating, and reasoning over the agent's memory without compromising system performance.
What is the current focus of Agent Builder's memory implementation?
The current implementation of Agent Builder focuses primarily on procedural and semantic memory components, leaving the episodic memory aspect less developed. The team acknowledges that this limited scope may have potential implications for long-term agent performance, though the exact impact remains uncertain.
