P3233–P3244 · 12 CLEAN after hard arXiv-grep

Sample of the band:

• P3233 (2609.26048) — FIRE: Failure-Informed Runtime Engineering for Reliable Language-Model Agents
• P3234 (2609.26056) — CricRAG: Retrieval Augmented Vision-Language Models for Personalized Cricket Coaching
• P3235 (2609.26057) — Observing the Conduct of Systematic Reviews with Generative AI Support: An Experience Report from a Graduate S
• P3236 (2609.26059) — Adversarial Course-of-Action Generation: Game-Theoretic Multi-Agent Algorithms for COA matching & COA generati
• P3237 (2609.26060) — ChainUQ: Reasoning Consistency-Aware Uncertainty Quantification for Large Language Models
• P3238 (2609.26069) — RankCert: When Can Simulated Learners Safely Select an AI Tutor? Robust Decision Certification Under Structura
• P3239 (2609.26072) — Policy-Backed Selective Regeneration under Tainted Inter-Agent Communication
• P3240 (2609.26076) — Selection-Invariant Communication Compilers for Privacy-Aware Multi-Agent LLM Workflows
• P3241 (2609.26087) — The Architect, the Adversary, and the Judge: Closed-Loop Generation of Standards-Aligned Assessment Items at S
• P3242 (2609.26095) — FusionMMT: A Unified Multimodal and Multitask Learning Framework for Nuclear Fusion
• P3243 (2609.26100) — TSS: Target-Side Sparsification for Speculative Decoding in Domain-Specific Large Language Models
• P3244 (2609.26105) — Neoadjuvant chemotherapy response prediction using pretreatment diffusion and contrast-enhanced magnetic reson

Cumulative unique CLEAN ≈ 2,314+ (prior ≈2,302+ through P3232 + 12). Standing two hundred seventy-seven; streak 880.