arXiv:2605.06327v1 Announce Type: cross Abstract: Safety benchmarks are routinely treated as evidence about how a language model will behave once deployed, but this inference is fragile if behavior depends on whether a prompt looks like an evaluation. We define evaluation-context…
arXiv:2605.05440v1 Announce Type: new Abstract: The security discussion around agentic AI focuses heavily on prompt injection. This paper argues that multi-agent systems also create a distinct authorization problem: maintaining authorization invariants as non-human principals retrieve data, delegate tasks, and synthesize…
arXiv:2605.06588v1 Announce Type: cross Abstract: Graph Edit Distance (GED) is a fundamental, albeit NP-hard, metric for structural graph similarity. Recent neural graph matching architectures approximate GED by first encoding graphs with a Graph Neural Network (GNN) and then applying either…
arXiv:2605.05460v1 Announce Type: new Abstract: The development of accurate exchange-correlation (XC) functionals remains a longstanding challenge in density functional theory (DFT). The vast majority of XC functionals have been hand designed by human researchers combining physical insight, exact constraints, and…
arXiv:2512.18034v3 Announce Type: replace Abstract: Discrete facility layout design involves placing physical entities to minimize handling costs while adhering to strict safety and spatial constraints. This combinatorial problem is typically addressed using Mixed Integer Linear Programming (MILP) or Constraint Programming…
arXiv:2605.05475v1 Announce Type: new Abstract: As AI systems increasingly exhibit autonomous, goal-directed, and long-horizon behavior, users lack a standardized way to detect the degree to which a system functions like an intentional actor for governance and accountability purposes. This position…
arXiv:2605.03989v2 Announce Type: replace Abstract: Retrieval-augmented generation systems often assume that one fixed retrieval pipeline is sufficient across heterogeneous tasks, yet factoid question answering, multi-hop reasoning, and scientific verification exhibit different retrieval preferences. We present Experience-RAG Skill, an agent-oriented pluggable…
arXiv:2603.05421v3 Announce Type: replace-cross Abstract: Compressing vision-language models for on-device deployment is increasingly important in clinical settings, but knowledge distillation (KD) degrades sharply when the teacher-student capacity gap spans an order of magnitude or more. We argue that, under such…
arXiv:2506.13727v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely deployed in real-world applications, yet their internal mechanisms remain difficult to interpret and control, limiting our ability to diagnose and correct undesirable behaviors. Mechanistic interpretability addresses this challenge by…
arXiv:2601.21351v2 Announce Type: replace-cross Abstract: Attentio-FFN disaggregation (AFD) is an emerging architecture for LLM decoding that separates state-heavy, KV-cache-dominated Attention computation from stateless, compute-intensive FFN computation, connected by per-step communication. While AFD enables independent scaling of memory and compute resources,…
