A 4B coding agent, post-trained only with RL on synthetic software tasks, reaches 61.5% on SWE-bench Verified and beats models many times larger. No distillation from a frontier teacher. The missing ingredient is not a bigger model. It is tasks calibrated to what the current checkpoint can almost, but not quite, solve.

The pipeline estimates how often the agent already resolves a candidate task, then rewrites the ones that are too easy or too hard until they sit in a learnable band. As the policy improves, the curriculum moves: from heavily scaffolded bug fixes toward shorter statements and more diverse change types. A simple tool harness (read, write, edit, glob, bash) lifts the same 4B base far more than it lifts large models. Failures remain mostly reasoning, not tool use. Effective reward hacking is held at zero by the harness, not by hoping the agent is honest.

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.

Most current AI agent research focuses on short-term tasks or narrow goals. Agentopia takes a different approach: it simulates entire lives.

The framework places 100 LLM-powered agents into persistent social worlds and runs their lives for 10 simulated years. Agents plan, form relationships, pursue personal growth, manage finances, experience setbacks, and make trade-offs between striving and well-being — all without heavy hand-engineering.