SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling
arXiv:2607.00095v1 Announce Type: new
Abstract: Generative models have emerged as scalable surrogates for physical simulation, yet they offer no guarantee that their outputs respect the conservation laws, boundary conditions, and nonlinear invariants that govern the underlying physics. Constrained ...
A Filtered Mixture-of-Generators for Fully Synthetic Survival Training
arXiv:2607.00127v1 Announce Type: new
Abstract: Survival analysis models time-to-event data, but in clinical settings training data are costly and scarce: events accrue over years of follow-up, cohorts are small, and privacy regulations restrict sharing across institutions. Tabular generative model...
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
arXiv:2607.00152v1 Announce Type: new
Abstract: Three of the most popular methods for training language models to reason look like three different tricks. They are not. All three adjust a single number: standard deviation, reflecting how much a prompt's sampled answers disagree. When such a model i...
Bounded Morality: Defining the Space of Moral Computation
arXiv:2607.00002v1 Announce Type: new
Abstract: Moral cognition has traditionally been modeled as adherence to fixed ethical theories--deontology, consequentialism, virtue ethics--implemented as static rules or value functions. We propose Bounded Morality, a formal framework for analyzing the compu...
The MMM Data Model -- A Normative Specification for Knowledge Interoperability in a Decentralisable Knowledge Commons
arXiv:2607.00032v1 Announce Type: new
Abstract: Many information systems are built around documents: self-contained units optimised for print production and linear reading. While effective for large-scale dissemination, the document-centric organisation constrains how knowledge can be structured, u...
Making Failure Safe: A Constrained, Verifiable Agent Framework for Open-Web Data Collection
arXiv:2607.00035v1 Announce Type: new
Abstract: LLMs and agents can generate web scrapers from natural-language requirements, but direct generation remains unreliable because of dependency errors, broken selectors, schema mismatches, and heterogeneous page structures. We propose a constrained, veri...
Multi-agent LLM systems are increasingly deployed as autonomous collaborators, where agents interact freely rather than execute fixed, pre-specified workflows. In such settings, effective coordination cannot be fully designed in advance and must instead emerge through interaction. However, most prio...
VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
Visual tokenizers map high-dimensional raw pixels into a compressed representation for downstream modeling. Beyond compression, tokenizers dictate what information is preserved and how it is organized. A de facto standard approach to video tokenization is to represent a video as a spatiotemporal 3D ...
Amortizing Maximum Inner Product Search with Learned Support Functions
Maximum inner product search (MIPS) is a crucial subroutine in machine learning, requiring the identification of a vector taken within a database (the keys) that best aligns with a given query. We propose amortized MIPS: a regression-based approach that trains neural networks to directly predict MIP...
On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs
Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its extension to vision language models (VLMs). While RL-tuned VLMs improve on visual reasoning benchmarks, they remain vulnerable to weak visual grou...
MemoryLLM: Plug-n-Play Interpretable Feed-Forward Memory for Transformers
Understanding how transformer components operate in LLMs is important, as it is at the core of recent technological advances in artificial intelligence. In this work, we revisit the challenges associated with interpretability of feed-forward modules (FFNs) and propose MemoryLLM, which aims to decoup...
Accelerometry-Derived Digital Biomarkers for Cardiometabolic Risk: A Population-Representative Tabular Benchmark with Uncertainty Quantification
arXiv:2606.30702v1 Announce Type: new
Abstract: Structured tabular data dominates clinical medicine, yet existing benchmarks fail to reflect real-world properties like complex survey sampling, demographic oversampling, and subgroup fairness. We introduce the NHANES Accelerometry Cardiometabolic Ben...
From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators
arXiv:2606.30704v1 Announce Type: new
Abstract: Large language models (LLMs) excel across a wide range of tasks, yet their instance-specific solutions often lack the structural consistency needed for reliable deployment. Workflows that encode recurring algorithmic patterns at the task level provide...
What Drives Interactive Improvement from Feedback?
arXiv:2606.30774v1 Announce Type: new
Abstract: We study when natural-language feedback produces improvement beyond the gains obtainable from repeated attempts alone. In multi-turn language agent setting, higher final accuracy can reflect useful feedback, but it can also arise from resampling, form...
Contrastive Reflection for Iterative Prompt Optimization
arXiv:2606.30840v1 Announce Type: new
Abstract: LLM agents are becoming central to information retrieval: they issue retrieval queries, synthesize answers, and increasingly serve as judges for IR evaluation. Improving the prompts that control these agents is an optimization problem, but in applied ...
BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation
arXiv:2606.30850v1 Announce Type: new
Abstract: Large language models (LLMs) are typically deployed in multi-turn conversations, where each turn provides new evidence that should reduce epistemic uncertainty about their environment. Acting rationally then requires inferring the unobserved quantitie...
AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement. Learn how SkillOpt turns skill editing into a training process, making agent behavior more reliable without changing model weights.
The post SkillOpt: Agent skills as trainable paramet...
Can AI Draw Science? A Benchmark for Evaluating Scientific Figure Generation by Text-to-Image and Multimodal Models
arXiv:2606.28406v1 Announce Type: new
Abstract: Text-to-image and multimodal generative models are increasingly used to produce scientific figures such as mechanism diagrams, experimental-design schematics, conceptual frameworks, and graphical abstracts. Yet existing image-generation benchmarks (e....
On the Necessity of a Liquid Substrate for Mesh Intelligence
arXiv:2606.28413v1 Announce Type: new
Abstract: A mesh of sovereign agents has no center: no shared clock, no shared model, and no coordinator to gather data or retrain. Its competence rests on each agent folding the projections its peers emit into a single internal state, online, from observations...
Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxy
arXiv:2606.28433v1 Announce Type: new
Abstract: One goal in reinforcement learning (RL) research is to understand general-purpose sequential decision-making, using benchmark simulators as a proxy for learning in deployment settings. When running experiments, however, the goal of achieving high perf...
Learning to Distributedly Estimate under Partially Known Dynamics: A Covariance-Agnostic Neural Kalman Consensus Filter
arXiv:2606.28441v1 Announce Type: new
Abstract: Online latent state estimation constitutes a fundamental challenge within the artificial intelligence field, serving as a foundational tool for diverse applications, including sequential decision making, anomaly and change-point detection. In this pap...
Recursive Self-Evolving Agents via Held-Out Selection
arXiv:2606.28374v1 Announce Type: new
Abstract: LLM agents are increasingly improved without weight updates by evolving a natural-language artifact, such as reflections, workflows, playbooks, cheatsheets, or optimized prompts, that conditions a frozen policy. Such methods are typically reported as ...
Data and Evaluation Closed-Loop for Model Capability Enhancement
arXiv:2606.28471v1 Announce Type: new
Abstract: Model capability is the central variable in LLM pre-training, yet is never observed directly: data shapes it prospectively, while evaluation reveals it only retrospectively, compressing samples, prompts, decoding, and scoring rules into one noisy scor...