arXiv:2609.22796v1 Announce Type: cross Abstract: Dialectal Arabic machine translation (MT) remains challenging despite recent progress in Arabic language…
Tag: AI
SelfOp: An Optimization Algorithm for Self-Improving Security Agents
arXiv:2609.22792v1 Announce Type: cross Abstract: LLM agents are increasingly used for security tasks: vulnerability discovery, exploit reproduction, and…
Analyzing Public Discourse on Urbanism: Topic Clustering, Sentiment Analysis and Retrieval-Augmented Generation using YouTube Comments
arXiv:2609.22705v1 Announce Type: cross Abstract: Online discourse about urban issues – walkability, cycling infrastructure, public transit, housing…
Parameterized Dense-Sparse Fusion for Hybrid Retrieval: Tuning a Rank-Score Mix on BEIR SciFact with Qdrant
arXiv:2609.22770v2 Announce Type: cross Abstract: We study a parameterized hybrid ranker that fuses a dense embedding list and a sparse lexical list. The…
From Code to Requirements: Agentic Reverse Engineering of Business Rules at Enterprise Scale
arXiv:2609.22719v1 Announce Type: cross Abstract: Business requirements for enterprise software systems are rarely captured in structured form; the logic…
Beyond Raw Engagement: A Counterfactual Observability Framework for Recommender Systems at Netflix
arXiv:2609.22747v1 Announce Type: cross Abstract: Understanding the performance of large-scale recommender systems remains an underexplored challenge,…
MATE: Policy-Aware Security Auditing for Mobile Agents via Synthesis-Driven Trajectory Learning
arXiv:2609.22724v1 Announce Type: cross Abstract: Mobile agents powered by foundation models now automate complex, multi-step workflows on real devices,…
Vision2CAD: A Visual Agent Harness for Explicit Geometry Referencing and Localization in Parametric CAD Modeling
arXiv:2609.22688v1 Announce Type: cross Abstract: Generating parametric CAD models requires accurate geometry and stable feature dependencies. Existing…
HIGenNTO: Scalable Humanoid Interaction Generation via Noise-Space Trajectory Optimization
arXiv:2609.22611v1 Announce Type: cross Abstract: Humanoid robots can acquire complex skills by imitating kinematic humanoid motion references, yet…
LLaDA-PRM: A Bidirectional Step-Level Reasoning Evaluator
arXiv:2609.22700v1 Announce Type: cross Abstract: Step-level reasoning evaluators are commonly based on autoregressive language models, whose causal…