This paper introduces MATTRL, a way for multiple AI agents to learn from their own conversations at test time using short, reusable text notes instead of retraining their weights.
This survey asks how close AI memory systems are to human memory and organizes the answer into three parts: implicit memory (inside the model), explicit memory (outside storage you can look up), and agentic memory (what an AI agent keeps over time to plan and act).
The paper shows that when we give AI lots of extra text, even harmless extra text, it can get badly confused—sometimes losing up to 80% of its accuracy.
KnowMe-Bench is a new test that checks if AI helpers truly understand a person, not just remember facts.
COMPASS is a new framework that turns a company’s rules into thousands of smart test questions to check if chatbots follow those rules.
The paper teaches small language models to predict open-ended future events by turning daily news into thousands of safe, graded practice questions.
This survey links how human brains remember things to how AI agents should remember things so they can act smarter over time.
Large language models can say things that sound right but aren’t supported by the given document; this is called a faithfulness hallucination.
Capitalization tie-out checks if a company’s ownership table truly matches what its legal documents say.
This paper organizes how AI agents learn and improve into one simple map with four roads: A1, A2, T1, and T2.
Large language models usually line words up in fixed order slots, which can waste mental energy and make it harder to find the important parts of a long or noisy text.
Clinical conversations are special because they mix caring feelings with precise medical facts, and old AI systems struggled to do both at once.