Most long-horizon agents compress or summarize the past as it arrives. That decision is made before future needs are known. Once discarded, the original evidence is gone.

Scroll treats each session as an executable environment. An append-only Event Log keeps lossless historical ground truth. A persistent Python kernel holds tool outputs, retrieved history, and derived state as variables rather than prompt text. The model writes code to search, materialize, and transform that state. Only the projections it prints enter the next working view.

Most work treats an LLM judge as a static artifact. It is built once, scored against a fixed benchmark, and then assumed to remain valid. In production that assumption fails. Data drifts, catalogs change, and the distribution of failures shifts. A judge that is not maintained will quietly lose alignment with human judgment.

A better model is a lifecycle. The judge must be born, trained, deployed, and continuously monitored. Birth defines the evaluation criteria and creates human-labeled benchmarks that include not only pass/fail labels but rationales. Training refines the rubrics so the judge rejects bad outputs for the right reasons, not merely the right labels. Deployment puts the same judge into two roles at once: a quality gate and a critic inside a generate-revise loop. Monitoring samples live outputs, compares them with ongoing human judgment, and triggers re-tuning when agreement drifts.

A new paradigm treats agent skills not as brittle prompts or expensive fine-tuning targets, but as an optimizable external text state — exactly like model parameters in deep learning.

SkillOpt introduces a systematic optimizer for natural-language skills: bounded edits, validation gates, meta-updates, and a clean separation between skill storage and execution. The result is compact, transferable, interpretable procedural rules that improve agent performance with zero additional inference cost.

A new paradigm treats memory not as passive retrieval or LLM fine-tuning, but as a separate, fully trainable model that can be plugged into any existing large language model.

MeMo introduces a modular framework with a novel data synthesis pipeline, model merging for continual learning, and a black-box inference protocol. It delivers strong performance on complex benchmarks like BrowseComp-Plus, NarrativeQA, and MuSiQue while keeping inference costs constant and remaining robust to noisy data.