Propose multiple subgoal decomposition plans for the current theorem using the information already gathered. Use when enough information has been collected from examples, counterexamples, search results, and previous failures to break the problem into several materially different plans.
Use this skill when the agent has enough context to propose several viable decomposition plans.
Read:
immediate_conclusions, toy_examples, and counterexamplesfailed_paths and branch_statesevents$direct-proving for a quick screening pass.Append one record per plan to subgoals:
{
"plan_id": "...",
"record_type": "decomposition_plan",
"goal": "...",
"plan_summary": "...",
"subgoals": ["..."],
"motivation": ["..."],
"uses_information_from": {
"examples": ["..."],
"counterexamples": ["..."],
"key_failures": ["..."],
"search_results": ["..."]
},
"status": "proposed|screening|screened|selected|failed|solved",
"branch_id": "optional"
}
Also append an events record summarizing the new plan set.
memory_searchmemory_appendbranch_updatesearch_arxiv_theoremsIf the agent cannot yet propose meaningful decomposition plans, append an events record with:
event_type="decomposition_plans_not_ready"