Tag
Procedural Memory Distillation (PMD) converts cross-episode signals from reinforcement learning rollouts into reusable procedural memory that is distilled into the policy weights during training, enabling self-improving language models without memory at inference. Experiments show PMD outperforms SDPO by 3.8-5.5% on SCIKNOWEVAL and 7.9-13.6% on LIVECODEBENCH.
Anchor is a task-generation pipeline that addresses artifact drift in AI agent benchmarks by jointly producing instructions, environments, solutions, and verifiers from a single constraint optimization specification, yielding consistent and auditable evaluation tasks for enterprise workflows. The paper introduces ERP-Bench, a benchmark of 300 long-horizon tasks in a production ERP system, showing that frontier models satisfy explicit constraints in 26.1% of trials but reach optimal solutions in only 17.4%.