Topic: agent memory

Latest on “agent memory”

The AI news that matters for people who make things — what happened, and how to put it to work in Grafy.

WikiTrace Links AI Agent Lessons to Their Source to Cut Errors

WikiTrace links each AI agent lesson back to the trajectory it came from, reducing memory-induced errors. The team reports gains across five benchmarks.

Try in Grafy Codeagent memorywikitracememory-induced degradationai research

Grafy Research Lab2 days ago6 min read

HiVe-Mem Tackles AI Memory for Multimodal Agents

Grafy Research Lab introduced HiVe-Mem, a multimodal agent memory framework blending horizontal expansion and vertical evidence. It aims at long AI.

Try in Graphmultimodal agentsai memory

arXiv AIOct 22, 20265 min read

REM Memory Framework Boosts Code Agent Reuse and Cuts Costs

A new REM framework lets LLM coding agents store, recall, and discard experiences more efficiently, improving bug‑fix success and lowering compute spend.

Try in Grafy Codellmagent memory