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.
1381
published research events
Latest work
A significant claim from a single source is published only after further confirmation.
The SPEM system stores individual skills and successful combinations of them for reuse. The authors report a success rate of 87.1 % in the ALFWorld environment and a reward of 38.38 % on the SkillsBench suite, with lower token usage and shorter runtime than the methods used for comparison.
MAMath-Bench contains 1 003 problems across 11 mathematical categories, incorporating text, images and audio. According to the study, collaboration among multiple agents does not consistently improve answer accuracy compared with strong standalone LLMs, and the systems remain vulnerable to injected errors in the reasoning process.
The Navalia framework turns corporate financial reports into tasks with traceable supporting evidence and programmatically verified answers for subsequent agent training. The authors report improvements over the baseline model Qwen3.6-35B-A3B across five test suites; the abstract does not state the size of the improvements.
A study of 421 Australian travellers links willingness to entrust travel planning to generative AI to the perceived reliability and accountability of providers. The available excerpt questions whether more explanation always strengthens trust, but does not include detailed results.
The authors have made the FairStress benchmark available for download. It examines whether persuasive arguments change model decisions differently across demographic groups. According to the authors, these differences appear even when the initial choice seems fair.
According to the authors, an agent using the GPT-4.1 model and rules created with the ALTK-Evolve method achieved a score of 67.5 % Pass^4 on τ²-bench retail: it succeeded in all four attempts on this proportion of tasks. The rules are generated by analyzing previous attempts without weight updates or human annotation.
The study introduces VibeTraining-Bench for iteratively improving AI agents within a fixed resource budget. According to the authors, the GPT-6-Astra model increased the target system's success rate on SWE-bench Verified from 32.9 % to 53.7 %. The code and data have been released.
The OR-License study tests 11 LLMs on 31 tasks across 10 industrial scenarios. None matched the overall quality of experts. The best-performing primary configuration of the Claude Code tool met strict feasibility requirements in 88.39 % of cases and achieved a DAQ score of 0.87 against a reference of 1.
The study introduces FlashMap, a method that proposes an entire block of tokens in a single pass and captures the dependencies between them. For Qwen3-8B, the authors report up to a 6.1-fold speedup with no loss of quality and an average speedup 7 % higher than that of the comparison method DFlash.
PatternBench evaluates seven classes of code optimizations and uses ASTs to verify that the intended change was made. According to the study, speedup alone is not enough to assess LLM capabilities, because some changes can already be handled by the compiler.
The authors present a system that offloads computations involving frozen weights to the NPU during LoRA training, while keeping adapters and optimization on the CPU. They evaluated it on two Qualcomm Snapdragon platforms with four models from the Qwen and Llama families. The abstract does not report numerical results.
According to the study, adding phonemes increased the accuracy of drug name pronunciation, as assessed by the Gemini model, from 54.6 % to 90.7 %. Human evaluators rated 84 % of recordings as correct, compared with 82 % for the best comparison method; the confidence intervals overlapped.
The study combines ZO to search for attack prefixes and FO to adjust the corresponding suffixes. According to the authors, the combination makes attacks more effective than either method alone; the order of optimization significantly affects the results. The evaluation also accounts for randomness in generation.
The authors introduce FusionRare, which combines four AI approaches. According to the study, it achieved Recall @1 of 51 % using phenotype data and 79 % when combining phenotype and genotype data across 2 528 clinical cases. In an evaluation involving physicians, it reduced the time to diagnosis by 21 %, according to the authors.
The authors introduced the PolyGraph method, which replaced 64 graphs with a single graph in a prototype and reduced graph preparation time from 3 915 to 93 ms with comparable median latency. The results come from synthetic runs on a single NVIDIA H800 GPU; this is not a production system.
The study introduces CME-SpectrumBench, with 190 questions based on simulated spectral data. When prompted directly, the models underperformed hand-written code; with access to a Python interpreter, they achieved comparable results, according to the authors.
The authors created vectors for 1 036 concepts using 2 million synthetic stories, which they are making publicly available. According to the abstract, the vectors identify the corresponding concepts across six models and influence model behavior when used to intervene in activations.
The study compared five variants of an agent on 668 tasks. Memory with free-form notes increased the first-attempt success rate by 4.6 percentage points, while memory supplemented with reusable code increased it by 2.8 points. The difference between the two designs was not statistically significant overall.
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 briefingAn overview of news from the past 24 hours and a main story when available. Beside them is Live · AI Flash, followed by research and links to other Radar sections. On mobile, the 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.