Personal project by Ulf Fäldt Reifenberg · unofficial, not affiliated with Bose or any other company

audio-exp-agent

An LLM agent that launches small audio ML experiments through a fixed set of tools and safeguards, and diagnoses runs that went wrong. Measured on CPU, on the Free Spoken Digit Dataset, against simple baselines. The agent does not win everywhere; the numbers below say where it does and does not.

Results

The setup

Task and data

Model and runs

Each run takes about half a second on CPU, so every experiment in this page was precomputed and stored in an append-only registry. The page makes no live model calls. The source data is Free Spoken Digit Dataset (CC BY-SA 4.0).

Tools and safeguards

ToolWhat it doesMode
launch_run(config)Validates the config against an allow-list, checks the budget, trains one run, appends it to the registry, returns validation accuracy.search
list_runs, run_status, get_metrics, compare_runsRead runs from the registry: status, metric history, config diff and data/code hash comparison between two runs.both
read_log(run_id, tail)Last lines of a run's training log.diagnose
get_split_info, get_feature_stats, get_audio_infoSpeakers per split and overlap; feature scale and normalisation; file vs declared sample rate.diagnose
write_report(text)Stores the agent's written summary in the registry.search
Safeguards, each covered by a unit test

Result 1: diagnosing faulty runs

Correct diagnoses by fault type

Result 2: hyper-parameter search at equal budget

Test accuracy of each search session (same training seed for paired sessions)

Result 3: do the numbers in the agent's report match the registry?

Example report and its check

Example agent traces

A good diagnosis

A failure

Limits

About. Personal project by Ulf Fäldt Reifenberg, built for a job application with coding agents. Unofficial, not affiliated with Bose. It shows how to wrap an LLM agent around training scripts with allow-lists, budgets, a sealed test set and a reproducible registry, and how to measure the agent against baselines. It does not show GPU or cluster scheduling, large-scale training, DSP or acoustic research, or anything about any company's internal systems. LLM calls were made once, offline, through Cloudflare Workers AI ( neurons); the page only reads results.json.