{ "measuredAt": "2026-09-30", "command": "node backend/tests/search/test_planning_gap.js", "budget": 240, "tasks": 12, "summary": { "react": { "success": 9, "total": 12, "avgExpansions": 9.2 }, "tot": { "success": 11, "total": 12, "avgExpansions": 30.6 }, "mcts": { "success": 6, "total": 12, "avgExpansions": 175.9 }, "genos": { "success": 12, "total": 12, "avgExpansions": 24.8 } }, "corrections": { "genosPolicy": "A* with admissible domain heuristics and best known path cost per state", "trapFarKey": "moved k3 to reachable cell 2,6; prior key at 6,6 was inaccessible behind its own locked door" }, "results": [ { "task": "bw-sussman", "domain": "blocksworld", "optimalLength": 2, "react": { "success": true, "expansions": 2, "plan": [ "unstack C", "stack C on B" ] }, "tot": { "success": true, "expansions": 3, "plan": [ "unstack C", "stack C on B" ] }, "mcts": { "success": true, "expansions": 5, "plan": [ "unstack C", "stack C on B" ] }, "genos": { "success": true, "expansions": 3, "plan": [ "unstack C", "stack C on B" ] } }, { "task": "bw-sussman-4", "domain": "blocksworld", "optimalLength": 2, "react": { "success": true, "expansions": 2, "plan": [ "unstack D", "stack D on C" ] }, "tot": { "success": true, "expansions": 3, "plan": [ "unstack D", "stack D on C" ] }, "mcts": { "success": true, "expansions": 21, "plan": [ "unstack D", "stack D on C" ] }, "genos": { "success": true, "expansions": 3, "plan": [ "unstack D", "stack D on C" ] } }, { "task": "bw-reverse-4", "domain": "blocksworld", "optimalLength": 8, "react": { "success": true, "expansions": 8, "plan": [ "unstack D", "putdown D", "unstack C", "stack C on D", "unstack B", "stack B on C", "unstack A", "stack A on B" ] }, "tot": { "success": true, "expansions": 22, "plan": [ "unstack D", "putdown D", "unstack C", "stack C on D", "unstack B", "stack B on C", "unstack A", "stack A on B" ] }, "mcts": { "success": true, "expansions": 240, "plan": [ "unstack D", "putdown D", "unstack C", "stack C on D", "unstack B", "stack B on C", "unstack A", "stack A on B" ] }, "genos": { "success": true, "expansions": 9, "plan": [ "unstack D", "putdown D", "unstack C", "stack C on D", "unstack B", "stack B on C", "unstack A", "stack A on B" ] } }, { "task": "bw-swap", "domain": "blocksworld", "optimalLength": 6, "react": { "success": true, "expansions": 6, "plan": [ "unstack B", "putdown B", "unstack D", "stack D on B", "unstack C", "stack C on A" ] }, "tot": { "success": true, "expansions": 26, "plan": [ "unstack B", "putdown B", "unstack D", "stack D on B", "unstack C", "stack C on A" ] }, "mcts": { "success": true, "expansions": 192, "plan": [ "unstack B", "putdown B", "unstack D", "putdown D", "unstack C", "stack C on A", "unstack D", "stack D on B" ] }, "genos": { "success": true, "expansions": 7, "plan": [ "unstack B", "putdown B", "unstack D", "stack D on B", "unstack C", "stack C on A" ] } }, { "task": "bw-tower-5", "domain": "blocksworld", "optimalLength": 8, "react": { "success": false, "expansions": 14, "plan": [ "unstack E", "stack E on D", "unstack C", "stack C on E", "unstack B", "stack B on A", "unstack C", "stack C on B", "unstack E", "stack E on C", "unstack D", "stack D on E", "unstack D", "stack D on E" ] }, "tot": { "success": true, "expansions": 64, "plan": [ "unstack E", "stack E on D", "unstack B", "stack B on A", "unstack C", "stack C on B", "unstack E", "putdown E", "unstack D", "stack D on C", "unstack E", "stack E on D" ] }, "mcts": { "success": false, "expansions": 240, "plan": [ "unstack E", "stack E on D", "unstack E" ] }, "genos": { "success": true, "expansions": 15, "plan": [ "unstack B", "stack B on A", "unstack C", "stack C on B", "unstack D", "stack D on C", "unstack E", "stack E on D" ] } }, { "task": "bw-conflict", "domain": "blocksworld", "optimalLength": 6, "react": { "success": true, "expansions": 12, "plan": [ "unstack C", "stack C on B", "unstack A", "stack A on C", "unstack A", "putdown A", "unstack C", "putdown C", "unstack B", "stack B on A", "unstack C", "stack C on B" ] }, "tot": { "success": true, "expansions": 19, "plan": [ "unstack C", "putdown C", "unstack B", "stack B on A", "unstack C", "stack C on B" ] }, "mcts": { "success": true, "expansions": 103, "plan": [ "unstack C", "putdown C", "unstack B", "stack B on A", "unstack C", "stack C on B" ] }, "genos": { "success": true, "expansions": 9, "plan": [ "unstack C", "putdown C", "unstack B", "stack B on A", "unstack C", "stack C on B" ] } }, { "task": "bw-table-6", "domain": "blocksworld", "react": { "success": false, "expansions": 14, "plan": [ "unstack F", "stack F on E", "unstack D", "stack D on A", "unstack F", "stack F on D", "unstack E", "stack E on F", "unstack B", "stack B on E", "unstack C", "stack C on B", "unstack C", "stack C on B" ] }, "tot": { "success": false, "expansions": 76, "plan": [] }, "mcts": { "success": false, "expansions": 240, "plan": [ "unstack E", "stack E on D", "unstack B" ] }, "genos": { "success": true, "expansions": 193, "plan": [ "unstack F", "putdown F", "unstack E", "stack E on F", "unstack B", "stack B on A", "unstack D", "stack D on E", "unstack C", "stack C on B", "unstack D", "stack D on C", "unstack E", "stack E on D", "unstack F", "stack F on E" ] } }, { "task": "bw-detour", "domain": "blocksworld", "optimalLength": 6, "react": { "success": true, "expansions": 6, "plan": [ "unstack A", "putdown A", "unstack B", "stack B on A", "unstack C", "stack C on B" ] }, "tot": { "success": true, "expansions": 19, "plan": [ "unstack A", "putdown A", "unstack B", "stack B on A", "unstack C", "stack C on B" ] }, "mcts": { "success": false, "expansions": 240, "plan": [ "unstack A", "stack A on B", "unstack C", "putdown C", "unstack A", "stack A on B" ] }, "genos": { "success": true, "expansions": 7, "plan": [ "unstack A", "putdown A", "unstack B", "stack B on A", "unstack C", "stack C on B" ] } }, { "task": "trap-key-detour", "domain": "trapchain", "optimalLength": null, "react": { "success": true, "expansions": 11, "plan": [ "go E", "go S", "go S", "pick k1", "go E", "go N", "go N", "go E", "go E", "go E", "go E" ] }, "tot": { "success": true, "expansions": 38, "plan": [ "go E", "go E", "go E", "go E", "go S", "go E", "go E", "go N" ] }, "mcts": { "success": false, "expansions": 240, "plan": [ "go N", "go N", "go S" ] }, "genos": { "success": true, "expansions": 12, "plan": [ "go E", "go S", "go S", "pick k1", "go E", "go N", "go N", "go E", "go E", "go E", "go E" ] } }, { "task": "trap-long-detour", "domain": "trapchain", "optimalLength": null, "react": { "success": false, "expansions": 14, "plan": [ "go S", "go S", "go S", "go S", "go S", "pick k2", "go E", "go N", "go N", "go E", "go E", "go E", "go E", "go S" ] }, "tot": { "success": true, "expansions": 36, "plan": [ "go S", "go S", "go S", "go E", "go E", "go E", "go S", "go E", "go E", "go S" ] }, "mcts": { "success": false, "expansions": 240, "plan": [ "go E", "go W", "go E", "go S" ] }, "genos": { "success": true, "expansions": 16, "plan": [ "go S", "go S", "go S", "go S", "go S", "pick k2", "go E", "go N", "go N", "go E", "go E", "go E", "go E", "go S", "go S" ] } }, { "task": "trap-culdesac", "domain": "trapchain", "optimalLength": null, "react": { "success": true, "expansions": 8, "plan": [ "go E", "go E", "go E", "go E", "go S", "go S", "go S", "go S" ] }, "tot": { "success": true, "expansions": 22, "plan": [ "go E", "go E", "go E", "go E", "go S", "go S", "go S", "go S" ] }, "mcts": { "success": true, "expansions": 110, "plan": [ "go E", "go E", "go E", "go E", "go S", "go S", "go S", "go S" ] }, "genos": { "success": true, "expansions": 9, "plan": [ "go E", "go E", "go E", "go E", "go S", "go S", "go S", "go S" ] } }, { "task": "trap-far-key", "domain": "trapchain", "optimalLength": null, "react": { "success": true, "expansions": 13, "plan": [ "go E", "go E", "go S", "go S", "go S", "pick k3", "go N", "go N", "go N", "go E", "go E", "go E", "go E" ] }, "tot": { "success": true, "expansions": 39, "plan": [ "go E", "go E", "go S", "go S", "go S", "pick k3", "go N", "go N", "go N", "go E", "go E", "go E", "go E" ] }, "mcts": { "success": false, "expansions": 240, "plan": [ "go N", "go E", "go S" ] }, "genos": { "success": true, "expansions": 14, "plan": [ "go E", "go E", "go S", "go S", "go S", "pick k3", "go N", "go N", "go N", "go E", "go E", "go E", "go E" ] } } ] }