A preprint is a signal, not a finished product or an independently confirmed result. We therefore track research papers separately and show the actual state of supporting evidence for each one.
846
published research events
Latest work
A significant claim from a single source is published only after further confirmation.
A study on arXiv describes a graph-based interface in which a shared graph neural network scores individual traffic movements at intersections, and each intersection constructs its own set of signal phases from these scores. Tests with PPO demonstrated transferability to new networks as well as sensitivity to changes in signal coverage.
Researchers described AgentKVShift on arXiv, a method for more efficient KV cache reuse in AI agent memory systems. According to the authors, it achieves performance close to full recomputation while refreshing only 10–30 % of the cache and speeds up prefill by 2–3.5× compared with an approach without reuse.
A study on arXiv points out that none of the leading AI labs publicly lists value pluralism as a goal, and there is no indication that deployed models are trained or tested for it. The authors propose three research directions to address this.
A survey among 10 experts and 15 respondents shows that companies often lack systematic processes for translating EU AI Act obligations into verifiable requirements. They see LLM tools for validation as promising, but not for full automation.
Researchers described LeafData, an agentic system that automatically generates a validated JSON configuration for data migration based on user instructions in a chatbot, executable directly on orchestration platforms.
Researchers described MoE²-LoRA on arXiv, a method for fine-tuning Mixture-of-Experts language models. The method uses a shared pool of LoRA experts and routing from the original model; according to the authors, it achieves the best accuracy results while preserving the general capabilities of the model.
A study from arXiv describes a new reward function for online RL training of reasoning models (LLM). According to the authors, it reduces the hallucination rate in long factual answers by 23.1 percentage points and increases the level of detail by 23 % without a loss of usefulness.
A study of two small vision-language models (Qwen2-VL-2B, SmolVLM) shows that verbally expressed confidence does not distinguish correct answers from incorrect ones, while internal token probability does - especially under image degradation and poor lighting.
A scientific paper presents a framework for controlling PDEs using JEPA and an MPPI controller. The key result: explicit physical observables (kinetic energy) work better than L2 distance in latent space. On a Navier–Stokes benchmark, KE-based planning reduces RMSE by 53 %.
FlowEvo, a research framework, enables LLM agents to improve continuously without training by compiling successful solutions into reusable skills. It links resource extraction, retrieval for future tasks, and filtering of unhelpful skills. On ALFWorld benchmarks…
Research on a framework for routing between LLM models in long-running agentic workflows. Unlike traditional routers that make decisions separately for each call, TRACE-Router assigns one model to a task and all LLM calls use it. The policy is updated according to the final outcome…
A research paper introduces DWT-Fusion, a training-free method for detecting language-model-generated text. It uses discrete wavelet analysis of token log-probabilities and achieves AUROC scores of 0.9919 on HC3, 0.8477 on M4, and 0.7471 on MAGE. It combines multiple configurations without supervised…
Research identifies an asymmetry in multimodal LLM safety: although they understand content regardless of visual style, their defenses can be bypassed with style-optimized modifications. The authors propose ASO, a module that uses a GRPO agent to amplify these attacks. The code is publicly available.
A research team created AgentRCA, a framework for automated fault diagnosis in industrial equipment. The system combines a model of normal dynamics with the capabilities of a language model and achieves competitive results without training on specific faults. It also provides readable explanations of the diagnosis.
A technical report from the ICML 2026 AI4Math Challenge describes an approach to physics problems involving text and images. A two-stage system extracts image content as text and orchestrates three different solvers through multi-agent debate. Accuracy improved from 0.643 to 0.802 on the public set; victory on both…
The research paper describes a multi-loop system of LLM agents for language learning that generates dialogue tailored to students’ CEFR level. In a pilot study with Japanese students, 87.4 % of sentences were within the expected level (compared with 54.1 % without adaptation). A statistically significant reduction in anxiety was not demonstrated…
A research study examines ungrounded content in podcasts generated by large language models. The authors created a dataset of over 1500 documents across five domains and proposed catch-n-repair to detect and repair incorrect conversational turns. Their analysis shows that even GPT-4o frequently inserts…
The research article shows that video world model failures in simulation tasks are caused by runtime infrastructure rather than the models. Request-centric serving loses non-recomputable state that is critical for backtracking. The authors propose a session-centric runtime with Persistent Computational State. Checkpoint/restore…
AI Radar monitors Czech and international sources every day, looking for changes that truly deserve attention.
MonitorsOfficial AI company blogs, specialist media, and research sources.
Selects and combinesFilters out information noise and combines articles about the same change into a single event.
Summarizes and explainsExplains significant events in English: what happened, why it matters and where the information comes from.
The result is a quick overview of what has actually changed in the AI world, rather than another stream of articles.
Use the CS/EN switch to read the same Radar in Czech or English. English content is published after its translation has been checked, so new and older items may appear later.
Everything you need to navigate the AI world
Today’s briefingThe “What is worth attention” selection sits beside Live · AI Flash, followed by research and links to other Radar sections. On mobile, these blocks appear one below another.
AI FlashAn ongoing feed of brief updates with an evidence status. Links lead to a Radar detail page when one is ready, otherwise to the original source. You can also find reset and outage histories here.
Practical applicationsWhat new tools and features can do, what you can try and what their actual impact could be.
Model selectionModel comparison by type of work, capabilities, price and speed.
Research and archiveA separate research overview, topic search and older events by date.
One event, everything that matters
Each row represents one event — not one article. At a glance, you can see its significance, credibility and main point.
Illustrative example, not a current news item.
Importance: ▮▮▮ majorOpenAIModels✓ 6
Agent mode is available to all paying users
Until now, the mode was available only on the highest plan; it is now available on all paid tiers without a waitlist.
▮▮▮ major · ▮▮ important · ▮ we're tracking = how significant the change is✓ 6 = six independent publishers, not the number of articles or feeds✓ official = a clear release, law or incident is substantiated by the relevant authority1 source = no independent confirmation yetbold = who is behind the changegray text = a brief summary of what happened
The detail page contains a fuller summary, its significance and original sources. Practical impact appears in the detail and the For individuals and For businesses views. An AI Flash item reaches the main selection only after it has been expanded and meets the publication rules.
The same news, two practical uses
We first summarize each event in the same way for everyone. Based on those same facts, we then explain what the change means for your own use and what it could mean for how a company operates.
For individualsWhat you can use or try, how the change can help you at work and what to watch out for.
For businessesWhat impact the change could have on processes, costs, risks and other business decisions.
Today’s briefing is the same for everyone. Pages
For individuals and For businesses
can be found in the main navigation — they select only events relevant to the given use case.
