arXiv:2603.29681v1 Announce Type: new Abstract: The common claim that generative AI simply amplifies the Dunning-Kruger effect is too coarse to capture the available evidence. The clearest findings instead suggest that large language model (LLM) use can improve observable output and short-term task performance while degrading metacognitive accuracy and flattening the classic competence-confidence gradient across skill […]
Symphony for Medical Coding: A Next-Generation Agentic System for Scalable and Explainable Medical Coding
arXiv:2603.29709v1 Announce Type: new Abstract: Medical coding translates free-text clinical documentation into standardized codes drawn from classification systems that contain tens of thousands of entries and are updated annually. It is central to billing, clinical research, and quality reporting, yet remains largely manual, slow, and error-prone. Existing automated approaches learn to predict a fixed set […]
StepCache: Step-Level Reuse with Lightweight Verification and Selective Patching for LLM Serving
arXiv:2603.28795v1 Announce Type: cross Abstract: We address LLM serving workloads where repeated requests share a common solution structure but differ in localized constraints, such as output schema, variable names, or numeric constants. Prior caching approaches typically reuse either full responses (semantic caching) or model-internal KV/prefix states, which are respectively brittle under partial changes or tightly […]
C-TRAIL: A Commonsense World Framework for Trajectory Planning in Autonomous Driving
arXiv:2603.29908v1 Announce Type: new Abstract: Trajectory planning for autonomous driving increasingly leverages large language models (LLMs) for commonsense reasoning, yet LLM outputs are inherently unreliable, posing risks in safety-critical applications. We propose C-TRAIL, a framework built on a Commonsense World that couples LLM-derived commonsense with a trust mechanism to guide trajectory planning. C-TRAIL operates through […]
Structured Intent as a Protocol-Like Communication Layer: Cross-Model Robustness, Framework Comparison, and the Weak-Model Compensation Effect
arXiv:2603.29953v1 Announce Type: new Abstract: How reliably can structured intent representations preserve user goals across different AI models, languages, and prompting frameworks? Prior work showed that PPS (Prompt Protocol Specification), a 5W3H-based structured intent framework, improves goal alignment in Chinese and generalizes to English and Japanese. This paper extends that line of inquiry in three […]
Byzantine-Robust and Communication-Efficient Distributed Training: Compressive and Cyclic Gradient Coding
arXiv:2603.28780v1 Announce Type: cross Abstract: In this paper, we study the problem of distributed training (DT) under Byzantine attacks with communication constraints. While prior work has developed various robust aggregation rules at the server to enhance robustness to Byzantine attacks, the existing methods suffer from a critical limitation in that the solution error does not […]
Optimizing Donor Outreach for Blood Collection Sessions: A Scalable Decision Support Framework
arXiv:2603.29643v1 Announce Type: new Abstract: Blood donation centers face challenges in matching supply with demand while managing donor availability. Although targeted outreach is important, it can cause donor fatigue via over-solicitation. Effective recruitment requires targeting the right donors at the right time, balancing constraints with donor convenience and eligibility. Despite extensive work on blood supply […]
A First Step Towards Even More Sparse Encodings of Probability Distributions
arXiv:2603.29691v1 Announce Type: new Abstract: Real world scenarios can be captured with lifted probability distributions. However, distributions are usually encoded in a table or list, requiring an exponential number of values. Hence, we propose a method for extracting first-order formulas from probability distributions that require significantly less values by reducing the number of values in […]
Reasoning-Driven Synthetic Data Generation and Evaluation
arXiv:2603.29791v1 Announce Type: new Abstract: Although many AI applications of interest require specialized multi-modal models, relevant data to train such models is inherently scarce or inaccessible. Filling these gaps with human annotators is prohibitively expensive, error-prone, and time-consuming, leading model builders to increasingly consider synthetic data as a scalable alternative. However, existing synthetic data generation […]
AgentFixer: From Failure Detection to Fix Recommendations in LLM Agentic Systems
arXiv:2603.29848v1 Announce Type: new Abstract: We introduce a comprehensive validation framework for LLM-based agentic systems that provides systematic diagnosis and improvement of reliability failures. The framework includes fifteen failure-detection tools and two root-cause analysis modules that jointly uncover weaknesses across input handling, prompt design, and output generation. It integrates lightweight rule-based checks with LLM-as-a-judge assessments […]
ATP-Bench: Towards Agentic Tool Planning for MLLM Interleaved Generation
arXiv:2603.29902v1 Announce Type: new Abstract: Interleaved text-and-image generation represents a significant frontier for Multimodal Large Language Models (MLLMs), offering a more intuitive way to convey complex information. Current paradigms rely on either image generation or retrieval augmentation, yet they typically treat the two as mutually exclusive paths, failing to unify factuality with creativity. We argue […]
ScoringBench: A Benchmark for Evaluating Tabular Foundation Models with Proper Scoring Rules
arXiv:2603.29928v1 Announce Type: new Abstract: Tabular foundation models such as TabPFN and TabICL already produce full predictive distributions yet prevailing regression benchmarks evaluate them almost exclusively via point estimate metrics RMSE R2 These aggregate measures often obscure model performance in the tails of the distribution a critical deficit for high stakes decision making in domains […]