Not all tokens are needed(NAT): token efficient reinforcement learning
arXiv:2603.06619v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a key driver of progress in large language models, but scaling RL to long chain-of-thought (CoT) trajectories is increasingly constrained by backpropagation over every generated token. Even with optimized rollout...
Advances in GRPO for Generation Models: A Survey
arXiv:2603.06623v1 Announce Type: new Abstract: Large-scale flow matching models have achieved strong performance across generative tasks such as text-to-image, video, 3D, and speech synthesis. However, aligning their outputs with human preferences and task-specific objectives remains challenging. Flow-GRPO extends Group Relative...
ERP-RiskBench: Leakage-Safe Ensemble Learning for Financial Risk
arXiv:2603.06671v1 Announce Type: new Abstract: Financial risk detection in Enterprise Resource Planning (ERP) systems is an important but underexplored application of machine learning. Published studies in this area tend to suffer from vague dataset descriptions, leakage-prone pipelines, and evaluation practices...
Orion: Characterizing and Programming Apple's Neural Engine for LLM Training and Inference
arXiv:2603.06728v1 Announce Type: new Abstract: Over two billion Apple devices ship with a Neural Processing Unit (NPU) - the Apple Neural Engine (ANE) - yet this accelerator remains largely unused for large language model workloads. CoreML, Apple's public ML framework,...
Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds
arXiv:2603.06729v1 Announce Type: new Abstract: Navigating safely through dense crowds requires collision avoidance that generalizes beyond the densities seen during training. Learning-based crowd navigation can break under out-of-distribution crowd sizes due to density-sensitive observation normalization and social-cost scaling, while analytical...
Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection
arXiv:2603.06745v1 Announce Type: new Abstract: Large Language Models (LLMs), despite advances in instruction tuning, often fail to follow complex user instructions. Activation steering techniques aim to mitigate this by manipulating model internals, but have a potential risk of oversteering, where...
Latent Autoencoder Ensemble Kalman Filter for Data assimilation
arXiv:2603.06752v1 Announce Type: new Abstract: The ensemble Kalman filter (EnKF) is widely used for data assimilation in high-dimensional systems, but its performance often deteriorates for strongly nonlinear dynamics due to the structural mismatch between the Kalman update and the underlying...
Reasoning Models Struggle to Control their Chains of Thought
arXiv:2603.05706v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising tool for detecting misbehaviors and understanding the motivations of modern reasoning models. However, if models can control what they verbalize in their CoT, it could undermine CoT monitorability. To...
SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
arXiv:2603.06333v1 Announce Type: new Abstract: Recursive self-improvement is moving from theory to practice: modern systems can critique, revise, and evaluate their own outputs, yet iterative self-modification risks subtle alignment drift. We introduce SAHOO, a practical framework to monitor and control...
EigenData: A Self-Evolving Multi-Agent Platform for Function-Calling Data Synthesis, Auditing, and Repair
arXiv:2603.05553v1 Announce Type: cross Abstract: Function-calling agents -- large language models that invoke tools and APIs -- require high-quality, domain-specific training data spanning executable environments, backing databases, and diverse multi-turn trajectories. We introduce EigenData, an integrated, self-evolving platform that automates...
DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality
arXiv:2603.05912v1 Announce Type: new Abstract: Search-augmented LLM agents can produce deep research reports (DRRs), but verifying claim-level factuality remains challenging. Existing fact-checkers are primarily designed for general-domain, factoid-style atomic claims, and there is no benchmark to test whether such verifiers...
The DSA's Blind Spot: Algorithmic Audit of Advertising and Minor Profiling on TikTok
arXiv:2603.05653v1 Announce Type: cross Abstract: Adolescents spend an increasing amount of their time in digital environments where their still-developing cognitive capacities leave them unable to recognize or resist commercial persuasion. Article 28(2) of the Digital Service Act (DSA) responds to...
Longitudinal Lesion Inpainting in Brain MRI via 3D Region Aware Diffusion
arXiv:2603.05693v1 Announce Type: cross Abstract: Accurate longitudinal analysis of brain MRI is often hindered by evolving lesions, which bias automated neuroimaging pipelines. While deep generative models have shown promise in inpainting these lesions, most existing methods operate cross-sectionally or lack...
NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution
arXiv:2603.05617v1 Announce Type: new Abstract: We present NOTAI.AI, an explainable framework for machine-generated text detection that extends Fast-DetectGPT by integrating curvature-based signals with neural and stylometric features in a supervised setting. The system combines 17 interpretable features, including Conditional Probability...
CodeScout: Contextual Problem Statement Enhancement for Software Agents
arXiv:2603.05744v1 Announce Type: new Abstract: Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements specification. Recent analysis of software engineering agents reveals that failures on such underspecified requests are highly correlated...
PVminerLLM: Structured Extraction of Patient Voice from Patient-Generated Text using Large Language Models
arXiv:2603.05776v1 Announce Type: new Abstract: Motivation: Patient-generated text contains critical information about patients' lived experiences, social circumstances, and engagement in care, including factors that strongly influence adherence, care coordination, and health equity. However, these patient voice signals are rarely available...
RouteGoT: Node-Adaptive Routing for Cost-Efficient Graph of Thoughts Reasoning
arXiv:2603.05818v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at multi-step reasoning, yet increasing the structural complexity of inference does not consistently improve system-level returns. Methods such as Tree of Thoughts (ToT), Graph of Thoughts (GoT), and Adaptive Graph...
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
arXiv:2603.05890v1 Announce Type: new Abstract: What happens when a storyteller forgets its own story? Large Language Models (LLMs) can now generate narratives spanning tens of thousands of words, but they often fail to maintain consistency throughout. When generating long-form narratives,...
Building an Ensemble LLM Semantic Tagger for UN Security Council Resolutions
arXiv:2603.05895v1 Announce Type: new Abstract: This paper introduces a new methodology for using LLM-based systems for accurate and efficient semantic tagging of UN Security Council resolutions. The main goal is to leverage LLM performance variability to build ensemble systems for...
Learning Next Action Predictors from Human-Computer Interaction
arXiv:2603.05923v1 Announce Type: new Abstract: Truly proactive AI systems must anticipate what we will do next. This foresight demands far richer information than the sparse signals we type into our prompts -- it demands reasoning over the entire context of...
CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report Evaluation
arXiv:2603.06183v1 Announce Type: new Abstract: We introduce CRIMSON, a clinically grounded evaluation framework for chest X-ray report generation that assesses reports based on diagnostic correctness, contextual relevance, and patient safety. Unlike prior metrics, CRIMSON incorporates full clinical context, including patient...
SPOT: Span-level Pause-of-Thought for Efficient and Interpretable Latent Reasoning in Large Language Models
arXiv:2603.06222v1 Announce Type: new Abstract: Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step pruning, they largely...
Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion
arXiv:2603.06264v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly being deployed in multilingual, multicultural settings, yet their reliance on predominantly English-centric training data risks misalignment with the diverse cultural values of different societies. In this paper, we present...
Abductive Reasoning with Syllogistic Forms in Large Language Models
arXiv:2603.06428v1 Announce Type: new Abstract: Research in AI using Large-Language Models (LLMs) is rapidly evolving, and the comparison of their performance with human reasoning has become a key concern. Prior studies have indicated that LLMs and humans share similar biases,...
Beyond Rows to Reasoning: Agentic Retrieval for Multimodal Spreadsheet Understanding and Editing
arXiv:2603.06503v1 Announce Type: new Abstract: Recent advances in multimodal Retrieval-Augmented Generation (RAG) enable Large Language Models (LLMs) to analyze enterprise spreadsheet workbooks containing millions of cells, cross-sheet dependencies, and embedded visual artifacts. However, state-of-the-art approaches exclude critical context through single-pass...
Score-Guided Proximal Projection: A Unified Geometric Framework for Rectified Flow Editing
arXiv:2603.05761v1 Announce Type: new Abstract: Rectified Flow (RF) models achieve state-of-the-art generation quality, yet controlling them for precise tasks -- such as semantic editing or blind image recovery -- remains a challenge. Current approaches bifurcate into inversion-based guidance, which suffers...
TML-Bench: Benchmark for Data Science Agents on Tabular ML Tasks
arXiv:2603.05764v1 Announce Type: new Abstract: Autonomous coding agents can produce strong tabular baselines quickly on Kaggle-style tasks. Practical value depends on end-to-end correctness and reliability under time limits. This paper introduces TML-Bench, a tabular benchmark for data science agents on...
Sparse Crosscoders for diffing MoEs and Dense models
arXiv:2603.05805v1 Announce Type: new Abstract: Mixture of Experts (MoE) achieve parameter-efficient scaling through sparse expert routing, yet their internal representations remain poorly understood compared to dense models. We present a systematic comparison of MoE and dense model internals using crosscoders,...
MoE Lens -- An Expert Is All You Need
arXiv:2603.05806v1 Announce Type: new Abstract: Mixture of Experts (MoE) models enable parameter-efficient scaling through sparse expert activations, yet optimizing their inference and memory costs remains challenging due to limited understanding of their specialization behavior. We present a systematic analysis of...
Self-Auditing Parameter-Efficient Fine-Tuning for Few-Shot 3D Medical Image Segmentation
arXiv:2603.05822v1 Announce Type: new Abstract: Adapting foundation models to new clinical sites remains challenging in practice. Domain shift and scarce annotations must be handled by experts, yet many clinical groups do not have ready access to skilled AI engineers to...