Self-Crystallizing Behavior Trees for Autonomous Drones
Overview
This research proposes Self-Crystallizing Behavior Trees (SCBT), a method that integrates foundation models into deterministic control systems for autonomous drones. SCBT uses an LLM as a compiler to generate and refine control patches during runtime, which are then crystallized into deterministic behavior trees. The approach demonstrates improved mission success rates compared to unpatched and hand-coded trees, though it faces challenges in correctly attributing certain failure scenarios.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · LLM calls: 11 other · Basis not reported · Differing source assertions
“tor. Over three seeds of a 20-episode learning phase with wind-gust and battery failures, SCBT used $11\pm1.4$ LLM calls against 26 for whole-tree regeneration and 22 without a library, with 0.33 calls per episode in the second half. The crystallized trees, 28 and 33 nodes with two patches each, reached $97\pm2\%$ mission success with no learning running, against 12\% for the unpatched tree and 98\% for a hand-coded”
Exact source · revision 1Source owner not reported
Reported quantity · LLM calls: 26 other · Basis not reported · Differing source assertions
“tor. Over three seeds of a 20-episode learning phase with wind-gust and battery failures, SCBT used $11\pm1.4$ LLM calls against 26 for whole-tree regeneration and 22 without a library, with 0.33 calls per episode in the second half. The crystallized trees, 28 and 33 nodes with two patches each, reached $97\pm2\%$ mission success with no learning running, against 12\% for the unpatched tree and 98\% for a hand-coded”
Exact source · revision 1Source owner not reported
Reported quantity · LLM calls: 22 other · Basis not reported · Differing source assertions
“tor. Over three seeds of a 20-episode learning phase with wind-gust and battery failures, SCBT used $11\pm1.4$ LLM calls against 26 for whole-tree regeneration and 22 without a library, with 0.33 calls per episode in the second half. The crystallized trees, 28 and 33 nodes with two patches each, reached $97\pm2\%$ mission success with no learning running, against 12\% for the unpatched tree and 98\% for a hand-coded”
Exact source · revision 1Source owner not reported
Reported quantity · LLM calls per episode: 0.33 other · Basis not reported
“tor. Over three seeds of a 20-episode learning phase with wind-gust and battery failures, SCBT used $11\pm1.4$ LLM calls against 26 for whole-tree regeneration and 22 without a library, with 0.33 calls per episode in the second half. The crystallized trees, 28 and 33 nodes with two patches each, reached $97\pm2\%$ mission success with no learning running, against 12\% for the unpatched tree and 98\% for a hand-coded”
Exact source · revision 1Source owner not reported
Reported quantity · nodes in crystallized trees: 28 other · Basis not reported
“tor. Over three seeds of a 20-episode learning phase with wind-gust and battery failures, SCBT used $11\pm1.4$ LLM calls against 26 for whole-tree regeneration and 22 without a library, with 0.33 calls per episode in the second half. The crystallized trees, 28 and 33 nodes with two patches each, reached $97\pm2\%$ mission success with no learning running, against 12\% for the unpatched tree and 98\% for a hand-coded”
Exact source · revision 1Source owner not reported
Evidence dependency changes (2)
- 2026-10-30T22:18:49.162Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T22:18:34.074Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalSelf-Crystalizing Behavior Trees: Amortizing Foundation-Model Reasoning into Deterministic Control for Autonomous Drones
This research proposes Self-Crystallizing Behavior Trees (SCBT), a method that integrates foundation models into deterministic control systems for autonomous drones. SCBT uses an LLM as a compiler to generate and refine control patches during runtime, which are then crystallized into deterministic behavior trees. The approach demonstrates improved mission success rates compared to unpatched and hand-coded trees, though it faces challenges in correctly attributing certain failure scenarios.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).