Test the real thesis: does a strong LLM (planner) + HTLM (grounder) beat the strong LLM doing its own grounding, on a live multi-step browser benchmark?
Controlled A/B, host tool browser-use (Python), benchmark browser-use BU Bench V1, planner via OpenRouter. Only the grounder call differs between arms:
- Baseline: strong LLM grounds its own sub-instruction.
- Treatment: HTLM local server grounds it.
Plan: .agents/plans/2026-07-15-htlm-planner-grounder-benchmark.md
Deliverables:
integration/htlm_server.py — local HTTP grounder (llama-cpp-python, GGUF, reuses data/pipeline/prompt.py + training/eval.py::_extract_action)integration/adapter.py — browser-use DOM ⇄ HTLM page-representation/action schema bridgeintegration/planner.py — OpenRouter strong-LLM planner + shortlist pruningintegration/loop.py — shared step loop, grounder strategy param (llm|htlm)integration/run_bench.py — BU Bench subset (n=20) runner + comparison table
Success = comparison table shows delta (HTLM arm vs LLM-grounding arm) on success rate, latency, cost. Ship integration only if delta favorable.
Test the real thesis: does a strong LLM (planner) + HTLM (grounder) beat the strong LLM doing its own grounding, on a live multi-step browser benchmark?
Controlled A/B, host tool browser-use (Python), benchmark browser-use BU Bench V1, planner via OpenRouter. Only the grounder call differs between arms:
Plan:
.agents/plans/2026-07-15-htlm-planner-grounder-benchmark.mdDeliverables:
integration/htlm_server.py— local HTTP grounder (llama-cpp-python, GGUF, reusesdata/pipeline/prompt.py+training/eval.py::_extract_action)integration/adapter.py— browser-use DOM ⇄ HTLM page-representation/action schema bridgeintegration/planner.py— OpenRouter strong-LLM planner + shortlist pruningintegration/loop.py— shared step loop, grounder strategy param (llm|htlm)integration/run_bench.py— BU Bench subset (n=20) runner + comparison tableSuccess = comparison table shows delta (HTLM arm vs LLM-grounding arm) on success rate, latency, cost. Ship integration only if delta favorable.