arXiv:2608.19932v1 Announce Type: new Abstract: Public cardiac cohorts annotate different subsets of the heart, so shapes from separate sources cannot be…
Category: AI
SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning
arXiv:2608.19842v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language…
TESTNAV: Pareto-Guided Search for Compositional Robustness Testing
arXiv:2608.19882v1 Announce Type: new Abstract: Deep learning models remain vulnerable to real-world input perturbations, especially when multiple…
EnvHarness: Awakening Static Worlds for Agent Learning
arXiv:2608.19880v1 Announce Type: new Abstract: LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind…
KnowledgeForge: mining gold from the ITSM ticket graveyard
KnowledgeForge mines resolved ITSM incident tickets into new knowledge base articles and automatically curates the existing library by deduplicating,…
Specification-delta-driven data governance: an empirical study of the {\guillemotleft}spec-delta{\guillemotright} as the unit of change in lakehouse data platforms
arXiv:2608.19838v1 Announce Type: new Abstract: Spec Driven Development SDD has consolidated the idea that the specification rather than the code should…
How Fanatics Betting and Gaming built a multi-agent customer support system
Fanatics Betting and Gaming built a multi-agent customer support system on AWS to handle the complexity of sports betting: state-specific rules, real-time…
PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents
arXiv:2608.19861v1 Announce Type: new Abstract: Customer-service LLM agents must follow organizational policy when acting on a user’s behalf. Compliance…
When Saying No Makes Better Videos: Designing Dual Gatekeeping for Pedagogically Grounded AI Content Creation
arXiv:2608.19812v1 Announce Type: new Abstract: To prevent the adoption of aesthetically polished but pedagogically flawed AI content, we study a video…
LLMs as Acquisition Policies for Finite-Pool Materials Optimization: A Controlled Study
arXiv:2608.19790v1 Announce Type: new Abstract: Discovering materials with desirable properties often requires searching large candidate spaces while…