arXiv:2605.20874v1 Announce Type: new Abstract: Enterprise agents are increasingly expected to operate autonomously across tools and interfaces, yet production deployments require governance by construction. Systems must specify which actions are allowed, when human oversight is required, and what information may be exposed, without rebuilding the agent for each domain. This demo presents CUGA’s policy system, […]
Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression
arXiv:2605.20740v1 Announce Type: cross Abstract: Large language models can predict real-valued quantities from heterogeneous inputs such as text, code, and molecular strings, but most training objectives score each decoded floating-point number independently, improving point estimates without ensuring calibrated predictive distributions. This limits applications requiring candidate ranking or uncertainty estimation. We introduce Distribution-Aware Reward, an on-policy […]
CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarking
arXiv:2602.08023v3 Announce Type: replace-cross Abstract: Existing benchmarks for LLM-based offensive security agents use isolated, single-target setups with a known vulnerable service and fixed objective. They measure exploitation effectively, but miss how real Capture-the-Flag (CTF) participants triage unknown surfaces, prioritize targets, and allocate effort under uncertainty. Current evaluations therefore fail to assess strategic reasoning beyond exploitation […]
PACD-Net: Pseudo-Augmented Contrastive Distillation for Glycemic Control Estimation from SMBG
arXiv:2605.20751v1 Announce Type: cross Abstract: Effective diabetes management requires continuous monitoring of glycemic levels. Clinically, glycemic control is assessed using metrics such as Time in Range (TIR), Time Below Range (TBR), and Time Above Range (TAR), typically derived from continuous glucose monitoring (CGM). However, many patients rely on self-monitoring of blood glucose (SMBG) due to […]
For How Long Should We Be Punching? Learning Action Duration in Fighting Games
arXiv:2605.20911v1 Announce Type: new Abstract: Fighting games such as Street Fighter II present unique challenges to reinforcement learning (RL) agents due to their fast-paced, real-time nature. In most RL frameworks, agents are hard-coded to make decisions at a fixed interval, typically every frame or every N frames. Although this design ensures timely responses, it restricts […]
GraphRAG on Consumer Hardware: Benchmarking Local LLMs for Healthcare EHR Schema Retrieval
arXiv:2605.20815v1 Announce Type: cross Abstract: Graph-based Retrieval Augmented Generation (GraphRAG) extends retrieval-augmented generation to support structured reasoning over complex corpora, but its reliability under resource-constrained, privacy-sensitive deployments remains unclear. In healthcare, where Electronic Health Record (EHR) data is complex and strictly regulated, reliance on cloud-based large language models (LLMs) introduces challenges in cost, latency, and […]
On Integrating Resilience and Human Oversight into LLM-Assisted Modeling Workflows for Digital Twins
arXiv:2603.25898v3 Announce Type: replace-cross Abstract: LLM-assisted modeling holds the potential to rapidly build executable Digital Twins of complex systems from only coarse descriptions and sensor data. However, resilience to LLM hallucination, human oversight, and real-time model adaptability remain challenging and often mutually conflicting requirements. We present three critical design principles for integrating resilience and oversight […]
Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards
arXiv:2605.20865v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) plays a pivotal role in improving the reasoning ability of large language models. However, widely used PPO surrogate objectives are fundamentally local, as they rely on a local approximation of the exact policy gradient objective. While this approximation improves stability by reducing the variance […]
Playing Devil’s Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy
arXiv:2605.21006v1 Announce Type: new Abstract: We study the effect of different persona on textbfsycophancy: model’s agreement with users even when the user is incorrect. The standard mitigation, Contrastive Activation Addition (CAA), derives a steering direction from labelled pairs of sycophantic and honest responses. This study evaluates whether off-the-shelf persona steering vectors, originally developed for general […]
Training distribution determines the ceiling of drug-blind cancer sensitivity prediction
arXiv:2605.20885v1 Announce Type: cross Abstract: Precision oncology requires predicting which drugs will suppress a specific tumor from its molecular profile, but drug-blind sensitivity prediction has plateaued despite increasingly complex drug representations. Here we show that this stagnation reflects a metric artifact rather than a representational bottleneck. The standard benchmark, global Pearson r, is dominated by […]
HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization
arXiv:2605.03562v3 Announce Type: replace-cross Abstract: KV-cache quantizers usually optimize storage-space reconstruction, even though attention reads keys through logits and values through attention-weighted readout. We argue that persistent cache error should be measured in model-visible coordinates. For keys, the visible object is score error modulo constant shifts; this yields HeadQ, a key-side method that stores a […]
Sutra: Tensor-Op RNNs as a Compilation Target for Vector Symbolic Architectures
arXiv:2605.20919v1 Announce Type: cross Abstract: Sutra is a typed, purely functional programming language whose compiled forward pass is a PyTorch neural network. The compiler beta-reduces the whole program — primitives, control flow, string I/O — to one fused tensor-op graph over a frozen embedding substrate. Rotation binding, unbind, bundle, polynomial Kleene three-valued logic, and tail-recursive […]