import argparseimport importlib.util from graph_reasoner.agent.backend import load_backend, resolve_kbfrom graph_reasoner.agent.eval import build_generate_seamfrom graph_reasoner.agent.gate import edge_dicts, gate_assertionfrom graph_reasoner.agent.loop import EpisodeConfig, drive_episode, start_episodefrom graph_reasoner.eval.parse import extract_final_answer, extract_graph_jsonfrom graph_reasoner.schema import BenchmarkItem QUESTION = ("In semiconductor metrology, which subsystem is typically paired with " "high-resolution nanoscale imaging techniques used for structural inspection?") def default_engine() -> str: for engine, package in (("mlx", "mlx_lm"), ("vllm", "vllm")): if importlib.util.find_spec(package) is not None: return engine return "hf" ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)ap.add_argument("--model", default=f"{default_engine()}:lamm-mit/Prospector-4B")ap.add_argument("--graph", default="tsmc", help="the substrate: tsmc, or biograph, pfas, matprop once downloaded")ap.add_argument("--question", default=QUESTION)args = ap.parse_args() graph = load_backend(args.graph, resolve_kb(args.graph, None))cfg = EpisodeConfig() # the paper's protocol: 20 tool calls, 1,024 tokens a turn, greedyseam = build_generate_seam(args.model, cfg) def generate(conversations, max_new_tokens): """The harness's generate call, printing the turn it is answering and the turn it gets back.""" print(conversations[0][-1]["content"], end="\n\n") out = seam(conversations, max_new_tokens) print(out[0], end="\n\n") return out item = BenchmarkItem(id="example", tier="adhoc", question=args.question, gold_answer="", gold_path={"nodes": [], "edges": []}, subgraph_edges=[], subgraph_text="")ep = drive_episode(start_episode(item, graph, cfg), graph, generate, cfg) answer = extract_final_answer(ep.final_text)cited = extract_graph_json(ep.final_text)verdict = gate_assertion(answer, edge_dicts(cited.edges if cited else None), edge_dicts(ep.seen.values()))print(f"answer: {answer}")print(f"gate: {'passed' if verdict['gate_pass'] else 'failed, ' + verdict['gate_reason']}; " f"{ep.n_calls} tool calls, {len(ep.seen)} edges seen")