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...
GPTNT: Benchmarking Real-Time Collaboration Between Multimodal Agents on Keep Talking And Nobody Explodes
arXiv:2606.28514v1 Announce Type: new
Abstract: Multimodal models are increasingly deployed to solve tasks collaboratively with humans or other artificial agents. Existing benchmarks show that these models possess many of the required component capabilities, but the conditions that coincide in coll...
IMCBench: A benchmark for multimodal LLMs in Image-grounded Medical Conversations
arXiv:2606.28556v1 Announce Type: new
Abstract: Recent advances in large language models and vision-language models have enabled reasoning over multimodal data, offering opportunities for clinical applications such as decision support and triaging. However, existing medical AI benchmarks are fragme...
Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
arXiv:2606.28589v1 Announce Type: new
Abstract: Current approaches to enhance Large Language Model (LLM) reasoning, such as Chain-of-Thought and "Wait" prompts, primarily encourage models to think more, yet often fail to guide them toward Truth. While Representation Editing (RepE) offers a intrinsi...
Millions of exploding stars could soon reveal dark energy's secrets
A new AI-powered framework could transform how astronomers measure the expansion of the Universe. By analyzing images of Type Ia supernovae and modeling their environments in unprecedented detail, researchers can estimate cosmic distances with near-spectroscopic accuracy. The technique is designed f...
Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
AI agents can't remember past conversations. They must constantly reload or retrieve context, which grows less efficient as tasks get longer and more complex. Memora solves this with a scalable memory system separating what’s stored from how it's retrieved.
The post Memora: A Harmonic Memory Represe...
arXiv:2606.27385v1 Announce Type: new
Abstract: The most widely used RANSAC variants score candidate models by counting inliers or summing per-point scores that saturate beyond a residual threshold. Every such score requires a user-supplied parameter that is a function of the inlier scale, which mu...
Unified Zero-Shot Time Series Forecasting: A Darts Foundation
arXiv:2606.27438v1 Announce Type: new
Abstract: Since its initial release in 2020, Darts has become a widely used open-source Python library for time series analysis. A series of foundation models have recently claimed accuracy improvements in zero-shot forecasting, promising a paradigm shift from ...
PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding
arXiv:2606.27440v1 Announce Type: new
Abstract: Foundation models for structural biology have achieved remarkable performance in predicting biomolecular structure and show promise for the design of proteins and small molecules. Yet understanding which internal features drive their outputs remains c...
AI-Model Network: Concept, Current State and Future
arXiv:2606.27382v1 Announce Type: new
Abstract: While the primary function of computers lies in computation and processing, the core value of the Internet is rooted in sharing and collaboration. Computers create the Internet, and the Internet empowers the value of computers. The rapid development o...
When Does Personality Composition Matter for Multi-Agent LLM Teams?
arXiv:2606.27443v1 Announce Type: new
Abstract: Personality prompting shapes how large language models communicate, yet whether these behavioral shifts affect objective task outcomes remains under-explored. Prior work shows that agents prompted with low agreeableness produce adversarial language, w...
Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning
arXiv:2606.27483v1 Announce Type: new
Abstract: Large language model (LLM) agents have demonstrated strong capability in sequential decision-making, yet they remains fundamentally reactive in long-horizon tasks. Unlike humans who employ "what-if" reasoning to evaluate potential plans before commitm...
Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models
arXiv:2606.27593v1 Announce Type: new
Abstract: We introduce a categorical framework called ODYSSEY for constructing verifiable, local truth-preserving foundation models as compositions of foundries: building-block architectural components that specify a cover of local contexts, local representatio...
DysLexLens: A Low-Resource LLM Framework for Analysing Dyslexic Learners Insights from Online Forums
arXiv:2606.27619v1 Announce Type: new
Abstract: Dyslexic learners increasingly use artificial intelligence (AI) tools to support reading, writing, organisation, and study-related tasks. However, their lived experiences with these tools remain largely underexamined. This paper proposes DysLexLens, a...
30 startups rebuilding enterprise software with AI agents
In Q1 2026, AI companies pulled in $242 billion in venture capital. That is 80% of all global VC funding for the quarter. From coding to compliance, customer service to clinical documentation, these 30 companies are not updating enterprise software. They are rebuilding it from scratch.
Implementation of reinforcement learning in chemical reaction networks: application to phototaxis as curiosity-driven exploration
arXiv:2606.26168v1 Announce Type: new
Abstract: Living systems navigate environments using noisy and incomplete sensory signals. In unicellular algae, phototaxis is often modeled as a mechanistic run--tumble process driven by stimulus--response rules. However, such descriptions overlook how organis...
KG-TRACE: A Neuro-Symbolic Framework for Mechanistic Grounding in Antimicrobial Resistance Prediction
arXiv:2606.26179v1 Announce Type: new
Abstract: While WGS-based AMR prediction has reached high accuracy, existing models lack a mechanism to ground neural attributions in established biological pathways. We present KG-TRACE, a novel neuro-symbolic framework that integrates the WHO mutation knowled...
Detecting and Controlling Sycophancy with Cascading Linear Features
arXiv:2606.26155v1 Announce Type: new
Abstract: Interpreting and controlling model behaviors through activation steering methods requires many pairs of contrastive samples that clearly exhibit desired or undesired behavior. These data pairs determine the degree to which interpretability frameworks ...
Refusal Lives Downstream of Persona in Chat Models
arXiv:2606.26161v1 Announce Type: new
Abstract: Linear directions in activation space have been identified for both refusal and persona traits in instruction-tuned chat models, but the two have been studied as separate mechanisms. We show they interact: a compliant persona gates refusal. In Qwen2.5...