Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents
arXiv:2608.20563v1 Announce Type: cross Abstract: Long-horizon security LLM agents must carry information and decisions across many dependent interactions, where later…
Towards Query-Agnostic RAG Evaluation via Query Coverage and Claim Verifiability
arXiv:2608.11238v2 Announce Type: replace Abstract: Retrieval-augmented generation improves the factuality of large language models by grounding responses in retrieved evidence,…
SDAD: Spec-Driven Agentic Development for the AI-Native SDLC
arXiv:2608.20341v1 Announce Type: new Abstract: Frontier coding agents backed by large language models with context windows from hundreds of thousands…
Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition
arXiv:2608.19885v2 Announce Type: replace-cross Abstract: After the inputs X are known, how much additional information does the label Y carry…
Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting
arXiv:2608.20761v1 Announce Type: cross Abstract: In non-stationary multivariate time series, different variables and samples often exhibit heterogeneous latent dynamic states,…
PSK at WMT 2026 MIST: Task-Specialized QLoRA Adapters for Multilingual Summarization and Question Answering
arXiv:2608.20757v1 Announce Type: cross Abstract: We describe the PSK submission to the WMT 2026 Multilingual Instruction Shared Task. Our system…
SuTRA : Structurally-Unified Tokenization with Root Awareness
arXiv:2608.18087v2 Announce Type: replace-cross Abstract: Existing subword tokenizers optimize statistical compression but ignore morphological structure, particularly the relationship between roots…
Active Inference as Context Acquisition for AI Agents
arXiv:2608.19202v1 Announce Type: new Abstract: Interactive AI agents must acquire the right context as efficiently as possible. When a user…
DA-WAM: Decision-Aligned Future Latents for Driving World Models
arXiv:2608.19085v2 Announce Type: replace-cross Abstract: Anticipating how scenes evolve under ego actions is fundamental to safe autonomous driving, yet the…
CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning
arXiv:2608.19776v1 Announce Type: cross Abstract: Current dexterous grasp planners primarily optimize for physical stability, focusing on whether an object can…