Metraipolis › archive › dc_75a0259cd33e
Teach-to-Crash: A Closed-Loop Student-Teacher LLM Framework for Collision-Inducing Test Scenario Generation — arXiv:2609.27296
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27296
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T08:57:24.432Z
- SHA-256 of the archived text
435501744ffa58cab6c99002048d0a10d833bad58a392a24434bc248963c7165- Stable URL of this page
https://metraipolis.com/documento/dc_75a0259cd33e
How to cite
Teach-to-Crash: A Closed-Loop Student-Teacher LLM Framework for Collision-Inducing Test Scenario Generation — arXiv:2609.27296 — arXiv (en), https://arxiv.org/abs/2609.27296 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75a0259cd33e (Metraipolis archive dc_75a0259cd33e, sha256 435501744ffa58cab6c99002048d0a10d833bad58a392a24434bc248963c7165)
BibTeX
@misc{dc75a0259cd33e,
title = {Teach-to-Crash: A Closed-Loop Student-Teacher LLM Framework for Collision-Inducing Test Scenario Generation — arXiv:2609.27296},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27296},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75a0259cd33e; sha256 435501744ffa58cab6c99002048d0a10d833bad58a392a24434bc248963c7165},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27296. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Validating Autonomous Driving Systems (ADS) in simulation requires testing architectures that can discover rare, safety-critical failures while generating scenarios that are executable, diverse, and useful for downstream failure analysis. We introduce Teach-to-Crash, a closed-loop testing framework that combines a constrained ego-centric scenario representation, stagnation-aware search control, and a dual-LLM architecture for adaptive failure discovery. A high-reasoning Teacher LLM acts as an adaptive search controller, while a low-reasoning Student LLM emits simulator-executable scenarios in a strict JSON schema. The Teacher intervenes only when rolling collision rate and time-to-collision metrics stagnate, providing strategic guidance to redirect the search. In a CARLA case study with two experimental setups that vary the ego vehicle's speed policy, Teach-to-Crash achieves the highest Collision Hit Rate (90.79%), the shortest mean Time-to-Collision (18.31 s), and a competitive Collision Discovery Rate (136.21). PAFOT attains a higher mean CDR (179.44), but with substantially larger variance. Teach-to-Crash also yields the highest diversity (0.547) and, averaged across both setups on the CARLA Traffic Manager controller, the highest avoidability-based usefulness proxy (60.04%) among the compared methods. These results, within the evaluated CARLA scope, provide evidence that closed-loop dual-LLM reasoning can steer adversarial simulation-based testing over a constrained executable program space, generating failures that are frequent, structurally diverse, and assessed as more frequently avoidable. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.MA). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA); Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2609.27296 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T08:03:18.944Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).