Generative artificial intelligence (AI) has rapidly become embedded in academic writing, assisting with tasks ranging from language editing to drafting text and producing evidence. Despite the wide range of AI use, the expectations for disclosure remain inconsistent. Several journals use binary disclosure statements that fail to distinguish minor language assistance from uses that have a […]
Debiasing Reward Models via Causally Motivated Inference-Time Intervention
arXiv:2604.27495v1 Announce Type: cross Abstract: Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often sensitive to spurious features such as response length. Existing inference-time approaches for mitigating these biases typically focus exclusively on response length, resulting in performance trade-offs. In this paper, we propose […]
Why Self-Supervised Encoders Want to Be Normal
arXiv:2604.27743v1 Announce Type: cross Abstract: We develop a geometric and information-theoretic framework for encoder-decoder learning built on the Information Bottleneck (IB) principle. Recasting IB as a rate-distortion problem with Kullback-Leibler (KL) divergence as distortion, we show that the optimal representation at any distortion level is a soft clustering of the emphpredictive manifold $mathcalM=p(Y$ inside the […]
PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains
arXiv:2508.21787v2 Announce Type: replace-cross Abstract: Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate solutions and selecting the one with the highest reward. The key challenge for reasoning tasks is designing a scoring function that can identify correct reasoning chains without access to ground-truth answers. […]
CausalCompass: Evaluating the Robustness of Time-Series Causal Discovery in Misspecified Scenarios
arXiv:2602.07915v2 Announce Type: replace-cross Abstract: Causal discovery from time series is a fundamental task in machine learning. However, its widespread adoption is hindered by a reliance on untestable causal assumptions and by the lack of robustness-oriented evaluation in existing benchmarks. To address these challenges, we propose CausalCompass, a flexible and extensible benchmark framework designed to […]
Rethinking Agentic Reinforcement Learning In Large Language Models
arXiv:2604.27859v1 Announce Type: new Abstract: Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large Language Models (LLMs) and increasingly complex, open-ended tasks has catalyzed a paradigm shift towards agentic paradigms within RL. This emerging framework extends beyond traditional RL […]
Collaborative Agent Reasoning Engineering (CARE): A Three-Party Design Methodology for Systematically Engineering AI Agents with Subject Matter Experts, Developers, and Helper Agents
arXiv:2604.28043v1 Announce Type: new Abstract: We present Collaborative Agent Reasoning Engineering (CARE), a disciplined methodology for engineering Large Language Model (LLM) agents in scientific domains. Unlike ad-hoc trial-and-error approaches, CARE specifies behavior, grounding, tool orchestration, and verification through reusable artifacts and systematic, stage-gated phases. The methodology employs a three-party workflow involving Subject-Matter Experts (SMEs), developers, […]
T-cell repertoire response in individuals with post-acute sequelae of COVID-19
arXiv:2604.26975v1 Announce Type: new Abstract: T-cells are central to SARS-CoV-2 clearance and immunological memory, yet their contribution to the persistence of post-acute sequelae of COVID-19 (PASC) remains poorly understood. The immunological features that distinguish individuals who develop PASC from those who recover fully are unresolved, in part due to the phenotypic heterogeneity of the condition […]
From Prompt to Physical Actuation: Holistic Threat Modeling of LLM-Enabled Robotic Systems
arXiv:2604.27267v1 Announce Type: cross Abstract: As large language models are integrated into autonomous robotic systems for task planning and control, compromised inputs or unsafe model outputs can propagate through the planning pipeline to physical-world consequences. Although prior work has studied robotic cybersecurity, adversarial perception attacks, and LLM safety independently, no existing study traces how these […]
Self-Evolving Software Agents
arXiv:2604.27264v1 Announce Type: cross Abstract: Autonomous agents can adapt their behaviour to changing environments, but remain bound to requirements, goals, and capabilities fixed at design time, preventing genuine software evolution. This paper introduces self-evolving software agents, combining BDI reasoning with LLMs to enable autonomous evolution of goals, reasoning, and executable code. We propose a BDI-LLM […]
SpatialGrammar: A Domain-Specific Language for LLM-Based 3D Indoor Scene Generation
arXiv:2604.27555v1 Announce Type: new Abstract: Automatically generating interactive 3D indoor scenes from natural language is crucial for virtual reality, gaming, and embodied AI. However, existing LLM-based approaches often suffer from spatial errors and collisions, in part because common scene representations-raw coordinates or verbose code-are difficult for models to reason about 3D spatial relationships and physical […]
WaferSAGE: Large Language Model-Powered Wafer Defect Analysis via Synthetic Data Generation and Rubric-Guided Reinforcement Learning
arXiv:2604.27629v1 Announce Type: new Abstract: We present WaferSAGE, a framework for wafer defect visual question answering using small vision-language models. To address data scarcity in semiconductor manufacturing, we propose a three-stage synthesis pipeline incorporating structured rubric generation for precise evaluation. Starting from limited labeled wafer maps, we employ clustering-based cleaning to filter label noise, then […]