Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation
arXiv:2603.10143v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) significantly improves the factuality of Large Language Models (LLMs), yet standard pipelines often lack mechanisms to verify inter- mediate reasoning, leaving them vulnerable to hallucinations in high-stakes domains. To address this, we...
OpenClaw-RL: Train Any Agent Simply by Talking
arXiv:2603.10165v1 Announce Type: new Abstract: Every agent interaction generates a next-state signal, namely the user reply, tool output, terminal or GUI state change that follows each action, yet no existing agentic RL system recovers it as a live, online learning...
Adaptive Activation Cancellation for Hallucination Mitigation in Large Language Models
arXiv:2603.10195v1 Announce Type: new Abstract: Large Language Models frequently generate fluent but factually incorrect text. We propose Adaptive Activation Cancellation (AAC), a real-time inference-time framework that treats hallucination-associated neural activations as structured interference within the transformer residual stream, drawing an...
GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning
arXiv:2603.10243v1 Announce Type: new Abstract: Recent studies show that the safety alignment of large language models (LLMs) can be easily compromised even by seemingly non-adversarial fine-tuning. To preserve safety alignment during fine-tuning, a widely used strategy is to jointly optimize...
Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation
arXiv:2603.10048v1 Announce Type: new Abstract: Sharpness-Aware Minimization (SAM) enhances generalization by minimizing the maximum training loss within a predefined neighborhood around the parameters. However, its practical implementation approximates this as gradient ascent(s) followed by applying the gradient at the ascent...
HTMuon: Improving Muon via Heavy-Tailed Spectral Correction
arXiv:2603.10067v1 Announce Type: new Abstract: Muon has recently shown promising results in LLM training. In this work, we study how to further improve Muon. We argue that Muon's orthogonalized update rule suppresses the emergence of heavy-tailed weight spectra and over-emphasizes...
A Survey of Weight Space Learning: Understanding, Representation, and Generation
arXiv:2603.10090v1 Announce Type: new Abstract: Neural network weights are typically viewed as the end product of training, while most deep learning research focuses on data, features, and architectures. However, recent advances show that the set of all possible weight values...
Denoising the US Census: Succinct Block Hierarchical Regression
arXiv:2603.10099v1 Announce Type: new Abstract: The US Census Bureau Disclosure Avoidance System (DAS) balances confidentiality and utility requirements for the decennial US Census (Abowd et al., 2022). The DAS was used in the 2020 Census to produce demographic datasets critically...
Hardware Efficient Approximate Convolution with Tunable Error Tolerance for CNNs
arXiv:2603.10100v1 Announce Type: new Abstract: Modern CNNs' high computational demands hinder edge deployment, as traditional ``hard'' sparsity (skipping mathematical zeros) loses effectiveness in deep layers or with smooth activations like Tanh. We propose a ``soft sparsity'' paradigm using a hardware...
DT-BEHRT: Disease Trajectory-aware Transformer for Interpretable Patient Representation Learning
arXiv:2603.10180v1 Announce Type: new Abstract: The growing adoption of electronic health record (EHR) systems has provided unprecedented opportunities for predictive modeling to guide clinical decision making. Structured EHRs contain longitudinal observations of patients across hospital visits, where each visit is...
Improving TabPFN's Synthetic Data Generation by Integrating Causal Structure
arXiv:2603.10254v1 Announce Type: new Abstract: Synthetic tabular data generation addresses data scarcity and privacy constraints in a variety of domains. Tabular Prior-Data Fitted Network (TabPFN), a recent foundation model for tabular data, has been shown capable of generating high-quality synthetic...
GSVD for Geometry-Grounded Dataset Comparison: An Alignment Angle Is All You Need
arXiv:2603.10283v1 Announce Type: new Abstract: Geometry-grounded learning asks models to respect structure in the problem domain rather than treating observations as arbitrary vectors. Motivated by this view, we revisit a classical but underused primitive for comparing datasets: linear relations between...
How to make the most of your masked language model for protein engineering
arXiv:2603.10302v1 Announce Type: new Abstract: A plethora of protein language models have been released in recent years. Yet comparatively little work has addressed how to best sample from them to optimize desired biological properties. We fill this gap by proposing...
On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
arXiv:2603.10397v1 Announce Type: new Abstract: One crucial factor behind the success of deep learning lies in the implicit bias induced by noise inherent in gradient-based training algorithms. Motivated by empirical observations that training with noisy labels improves model generalization, we...
Abandoning the separation of powers in times of war
Courtly Observations is a recurring series by Erwin Chemerinsky that focuses on what the Supreme Court’s decisions will mean for the law, for lawyers and lower courts, and for people’s lives. […]The postAbandoning the separation of powers in times of...
WordPress debuts a private workspace that runs in your browser via a new service, my.WordPress.net
WordPress’s new browser-based service lets users create private sites without hosting or signing up, turning the platform into a personal workspace for writing, research, and AI tools.
What is a Tort?
What is a tort, and what is tort law for? On one leading scholarly account, torts are legal liability rules that seek to promote the welfare of society at large by disincentivizing socially suboptimal behavior and distributing the costs of...
Curveball Steering: The Right Direction To Steer Isn't Always Linear
arXiv:2603.09313v1 Announce Type: new Abstract: Activation steering is a widely used approach for controlling large language model (LLM) behavior by intervening on internal representations. Existing methods largely rely on the Linear Representation Hypothesis, assuming behavioral attributes can be manipulated using...
Social-R1: Towards Human-like Social Reasoning in LLMs
arXiv:2603.09249v1 Announce Type: new Abstract: While large language models demonstrate remarkable capabilities across numerous domains, social intelligence - the capacity to perceive social cues, infer mental states, and generate appropriate responses - remains a critical challenge, particularly for enabling effective...
The Confidence Gate Theorem: When Should Ranked Decision Systems Abstain?
arXiv:2603.09947v1 Announce Type: new Abstract: Ranked decision systems -- recommenders, ad auctions, clinical triage queues -- must decide when to intervene in ranked outputs and when to abstain. We study when confidence-based abstention monotonically improves decision quality, and when it...
Logics-Parsing-Omni Technical Report
arXiv:2603.09677v1 Announce Type: new Abstract: Addressing the challenges of fragmented task definitions and the heterogeneity of unstructured data in multimodal parsing, this paper proposes the Omni Parsing framework. This framework establishes a Unified Taxonomy covering documents, images, and audio-visual streams,...
Meissa: Multi-modal Medical Agentic Intelligence
arXiv:2603.09018v1 Announce Type: new Abstract: Multi-modal large language models (MM-LLMs) have shown strong performance in medical image understanding and clinical reasoning. Recent medical agent systems extend them with tool use and multi-agent collaboration, enabling complex decision-making. However, these systems rely...
Time, Identity and Consciousness in Language Model Agents
arXiv:2603.09043v1 Announce Type: new Abstract: Machine consciousness evaluations mostly see behavior. For language model agents that behavior is language and tool use. That lets an agent say the right things about itself even when the constraints that should make those...
TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation
arXiv:2603.09341v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) helps large language models (LLMs) answer knowledge-intensive and time-sensitive questions by conditioning generation on external evidence. However, most RAG systems still retrieve unstructured chunks and rely on one-shot generation, which often yields...
Reward Prediction with Factorized World States
arXiv:2603.09400v1 Announce Type: new Abstract: Agents must infer action outcomes and select actions that maximize a reward signal indicating how close the goal is to being reached. Supervised learning of reward models could introduce biases inherent to training data, limiting...
Abundant Intelligence and Deficient Demand: A Macro-Financial Stress Test of Rapid AI Adoption
arXiv:2603.09209v1 Announce Type: new Abstract: We formalize a macro-financial stress test for rapid AI adoption. Rather than a productivity bust or existential risk, we identify a distribution-and-contract mismatch: AI-generated abundance coexists with demand deficiency because economic institutions are anchored to...
Automated Thematic Analysis for Clinical Qualitative Data: Iterative Codebook Refinement with Full Provenance
arXiv:2603.08989v1 Announce Type: new Abstract: Thematic analysis (TA) is widely used in health research to extract patterns from patient interviews, yet manual TA faces challenges in scalability and reproducibility. LLM-based automation can help, but existing approaches produce codebooks with limited...
Telogenesis: Goal Is All U Need
arXiv:2603.09476v1 Announce Type: new Abstract: Goal-conditioned systems assume goals are provided externally. We ask whether attentional priorities can emerge endogenously from an agent's internal cognitive state. We propose a priority function that generates observation targets from three epistemic gaps: ignorance...
One Language, Two Scripts: Probing Script-Invariance in LLM Concept Representations
arXiv:2603.08869v1 Announce Type: new Abstract: Do the features learned by Sparse Autoencoders (SAEs) represent abstract meaning, or are they tied to how text is written? We investigate this question using Serbian digraphia as a controlled testbed: Serbian is written interchangeably...
Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational Awareness
arXiv:2603.09231v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate exceptional performance on general-purpose tasks. however, transferring them to complex engineering domains such as space situational awareness (SSA) remains challenging owing to insufficient structural alignment with mission chains, the absence...