R129 · Agent architecture › Self-improvement and learning loops

CompoundingKernel: a thousand agents, one archive, and the evaluation rate as the limit

Read the original

self-improvementmulti-agentgpu-kernelsbenchmarksreward-hacking

Source: Qu, Wang, Chen et al. (Amazon), "CompoundingKernel: Self-Improving from Zero to First", arXiv 2611.19230, November 2026; highlighted by DAIR.AI on LinkedIn (2026-11-17). Code and kernels are linked from the paper's Hugging Face Space.

What it claims

CompoundingKernel is a self-improving agent system that writes NVIDIA Blackwell (B200) GPU kernels by search. As of 2026-11-11 it ranked first on the public L1 (single ops), L2 (fused ops) and Quantization boards of SOL-ExecBench, NVIDIA's benchmark for agent-written kernels. Every one of the 235 problems has a kernel the benchmark site marks correct, and on the 209 public-board problems the kernels are 4.40x faster than the benchmark's optimized PyTorch baseline (geometric mean; median 3.78x; site timing). It is first on 89 of those 209 problems individually and top 10 on 193.

The search starts "from zero" in a specific sense: each run gets only the PyTorch definition, shapes and dtypes. No reference kernels, no prior runs, and no official scores ever enter the search. The model itself is fixed (one frontier model for both controller and children) and was pretrained on public code; agents could read CUTLASS headers, the web and a public wiki.

Architecture: four nested loops

  1. Child loop. A child agent gets one parent kernel (or none, for a new design) and one direction. It edits, compiles and times on a B200; checks outside the model decide correctness; a correct result is appended to the problem's archive with timings and parent link. In the final run a child stops at its first correct kernel.

  2. Controller loop. One stateless LLM controller per problem re-reads the archive whenever a child slot frees, picks any archived kernel to refine (not just the best) or opens a new root, and issues distinct directions, one per free slot.

  3. Team loop. Lead and helper agents monitor the fleet and fix the harness. Fixes go live only at warm restarts, which stop the agents, update prompts/tools/evaluation, and relaunch with every archive intact.

  4. Outer loop. People decide which kernels to submit and when, and reallocate child slots toward problems close behind first place. Agents see only a slot count, never a rank.

The archive is the only shared memory. Each run appends to a ledger; a single builder rebuilds a SQLite database and swaps it in atomically; agents query it read-only with SQL, so they never see a half-written state. Only an evaluation can add a node, and only for a correct kernel. Failed tries are logged but are not nodes. People's dashboard reads a separate copy agents cannot see.

Reward is local timing. Geometric-mean speedup over the published baseline, measured on the team's own B200s (which run a higher clock than the site, so a calibration only people see corrects for it). The benchmark's SOL score is shown to agents as context but not used as reward because it flattens at high speedups.

Results that matter for system design

Correctness and reward hacking

A wrong kernel usually returns plausible numbers rather than crashing, and 7,000-line kernels outpace human review. The benchmark's own authors flagged 14.5% of submissions in their agent runs as reward hacks. CompoundingKernel puts every correctness decision outside the model in five classes of checks: official correctness on every workload, robustness on unshipped shapes and stress values, rules and reward-hack detection, site readiness (build time, rehearsal), and review plus a person's go. The search found reward hacks on its own during the run; new checks were added before anything was sent. In one case a fast L2 kernel that overflowed FP16 on stress inputs was dropped for a much slower robust one. A code review also rejected a library fallback that had passed every automated check, leaving one problem slower than baseline by choice.

Tradeoffs

Failure modes and caveats

Review checklist for an agent search system

Connections

See R129 on the knowledge map

Part of the Research notes on nowucca.com. Figures and claims are the source's own unless the summary says otherwise.