ClawLoop closes task synthesis, training, and failure diagnosis into one loop so harness-based agents improve without an external teacher model, beating the one-shot ClawGym pipeline on SkillsBench, Claw-Eval-Live, and ClawGym-Bench.
GraphForge is an evidence-graph framework that starts from O*NET occupation seeds, crawls real files into a workspace, builds an evidence graph over their relations, and compiles that graph into task statements and rubrics, with an initial rollout and a revision agent checking executability; fine-tuning Qwen3.6-27B on 2,169 trajectories brings GDPVal to 1445.7 (+65.7) under OpenHands and Workspace-Bench-Lite and SpreadsheetBench II to 63.7 (+7.7) and 24.0 (+13.7) under Claude Code, with the same data also improving Qwen3.6-35B-A3B.
This work implements a training-free incremental memory-maintenance runtime for a quantized Qwen hybrid recurrent–attention model that removes superseded attention KV entries, computes replacement records at the true sequence tail, and preserves the continuing recurrent state and unchanged KV; experiments show that independent block composition weakens query-conditioned memory selection, that true-tail updates preserve key current-state and historical bindings across eight scripted maintenance rounds, that slot-preserving alternatives repeat a double-subtraction error, and that attention-distribution proximity alone does not explain these semantic differences.
You’re all caught up