#self-improvement

6 articles

01 ·Agents·★ MEMBER·PAPER·8 min read Paper Walkthrough: S³Gym — Does Self-Testing and Self-Judging Add Up to Self-Improvement? Can an LLM agent really learn from its own experience? A benchmark that separates permissive exploration from strict held-out evaluation across seven games, comparing raw history, summary memory, and parameter training under one protocol. 02 ·Large Language Models·★ MEMBER·PAPER·13 min read Paper Explained: FlowBalance — Verifier-Grounded Self-Improvement from a Model's Own Reasoning Learning from your own answers breaks in two ways: the grading is too sparse, or you believe your own confidence. FlowBalance fixes both with one move — let the verifier decide the sign of the dense self-score — and learns a normalized distribution over whole responses. Explained from first principles. 03 ·Agents·★ MEMBER·PAPER·12 min read HarnessDev explained (arXiv:2609.01437) — agent harness benchmark Identical weights, different harness: GPT-5 solves 35.2% of Terminal-Bench 2.1 inside Terminus 2 and 49.6% inside Codex CLI. HarnessDev asks whether a model can build its own harness from a useless seed — and what survives held-out tasks. 04 ·Evaluation & Judging·★ MEMBER·PAPER·12 min read Self-Improving AI — Self-Play, Co-Evolution, and Generated Curricula What has to be true for a model to get better without anyone adding data? This article pulls three conditions out of AlphaZero's self-play, shows exactly which one breaks first for language models, explains how co-evolution and generated curricula try to patch the gap, and ends with why self-improvement claims are unusually easy to evaluate wrong. 05 ·Agents·★ MEMBER·PAPER·15 min read Paper Walkthrough: PILOT in the Loop — Fixing the Run While It Is Still Running Agent self-improvement that only starts after execution ends arrives too late. A ground-up walkthrough of PILOT, a supervisor–worker harness that redirects the live run while distilling skills from it, from intuition to equations to measured numbers and stated limits. 06 ·Agents·FREE·PAPER·8 min read Paper Walkthrough: Macaron-V1 — A Frozen Base plus a Mixture of LoRAs, Built to Keep Learning After Launch A guided tour of Mind Lab's open agent-model family Macaron-V1, straight from the paper: the Mixture-of-LoRA architecture that stacks four specialist adapters on a frozen 744B base and picks one per turn, and the recursive self-improvement loop that trains the model and its harness as a versioned pair.