▲ RESEARCH

## Articles

• 2026-10-09Recall without summarizing: agent memory on LoCoMo and LongMemEval
  We measured Logposa Graph against Entire Graph and Mem0 on 1,540 LoCoMo questions, then against Entire on 400 LongMemEval questions. Accuracy is neck and neck with Entire, search is tens of times faster, indexing calls no language model, and every answer traces back to its line.
• 2026-09-24PR fatigue, in numbers: when writing outpaces review
  AI tools made writing code cheap and left reading it as expensive as ever. What review studies and AI adoption data can tell us about the pressure on reviewers, and five signals to track on your team.
• 2026-07-28Why agent-written code needs a verifiable paper trail
  Agent changes can lose the instructions, observations, and human decisions that explain them. Here is the evidence worth preserving and what verification can establish.