Group Relative Policy Optimization (GRPO) was introduced and used successfully to train DeepSeek R1 models for promoting reasoning capabilities of LLMs using verifiable or binary rewards. We show in this paper that GRPO with verifiable rewards can be written as a Kullback Leibler ($\mathsf{KL}$) regularized contrastive loss, where the contrastive samples are synthetic data sampled from the old policy. The optimal GRPO policy $\pi_{n}$ can be expressed explicitly in terms of the binary reward, as well as the first and second order statistics of the old policy ($\pi_{n-1}$) and the reference policy $\pi_0$. Iterating this scheme, we obtain a sequence of policies $\pi_{n}$ for which we can quantify the probability of success $p_n$. We show that the probability of success of the policy satisfies a recurrence that converges to a fixed point of a function that depends on the initial probability of success $p_0$ and the regularization parameter $\beta$ of the $\mathsf{KL}$ regularizer. We show that the fixed point $p^*$ is guaranteed to be larger than $p_0$, thereby demonstrating that GRPO effectively amplifies the probability of success of the policy.

After being one of the first companies to roll out a Deep Research feature at the end of last year, Google is now making that same tool available to everyone. Starting today, Gemini users can try Deep Research for free in more than 45 languages -- no Gemini Advanced subscription necessary. For the uninitiated, Deep Research allows you to ask Gemini to create comprehensive but easy-to-read reports on complex topics. Compared to say Google's new AI Mode, Deep Research works slower than your typical chatbot, and that's by design. Gemini will first create a research plan before it begins searching the web for information that may be relevant to your prompt.

In late 2023, a team of third party researchers discovered a troubling glitch in OpenAI's widely used artificial intelligence model GPT-3.5. When asked to repeat certain words a thousand times, the model began repeating the word over and over, then suddenly switched to spitting out incoherent text and snippets of personal information drawn from its training data, including parts of names, phone numbers, and email addresses. The team that discovered the problem worked with OpenAI to ensure the flaw was fixed before revealing it publicly. It is just one of scores of problems found in major AI models in recent years. In a proposal released today, more than 30 prominent AI researchers, including some who found the GPT-3.5 flaw, say that many other vulnerabilities affecting popular models are reported in problematic ways.

The news: Google DeepMind has released a new model, Gemini Robotics, that combines its best large language model with robotics. Plugging in the LLM seems to give robots the ability to be more dexterous, work from natural-language commands, and generalize across tasks. All three are things that robots have struggled to do until now. Why it matters: The team hopes their work could usher in an era of robots that are far more useful and require less detailed training for each task. Incorporating LLMs into robotics is part of a growing trend, and this may be the most impressive example yet.

Peter Kyle, the UK's secretary of state for science, innovation and technology, has said he uses ChatGPT to understand difficult concepts The UK's technology secretary, Peter Kyle, has asked ChatGPT for advice on why the adoption of artificial intelligence is so slow in the UK business community – and which podcasts he should appear on. This week, Prime Minister Keir Starmer said that the UK government should be making far more use of AI in an effort to increase efficiency. "No person's substantive time should be spent on a task where digital or AI can do it better, quicker and to the same high quality and standard," he said. Now, New Scientist has obtained records of Kyle's ChatGPT use under the Freedom of Information (FOI) Act, in what is believed to be a world-first test of whether chatbot interactions are subject to such laws. These records show that Kyle asked ChatGPT to explain why the UK's small and medium business (SMB) community has been so slow to adopt AI.

The Trump administration is prioritizing the critical role of artificial intelligence in creating and upholding freedom. Just three weeks in, Vice President JD Vance declared at a global AI summit in Paris that AI "will make people more productive, more prosperous, and more free. The United States of America is the leader in AI, and our administration plans to keep it that way." To achieve this, the White House is working toward an AI action plan and calling on leading American AI companies to submit our best ideas. OpenAI is pleased to submit proposals today on a range of important considerations for AI from national security, to infrastructure and energy, to the federal government's own use of AI.

Recent advancements in reasoning with large language models (RLLMs), such as OpenAI-O1 and DeepSeek-R1, have demonstrated their impressive capabilities in complex domains like mathematics and coding. A central factor in their success lies in the application of long chain-of-thought (Long CoT) characteristics, which enhance reasoning abilities and enable the solution of intricate problems. However, despite these developments, a comprehensive survey on Long CoT is still lacking, limiting our understanding of its distinctions from traditional short chain-of-thought (Short CoT) and complicating ongoing debates on issues like "overthinking" and "test-time scaling." This survey seeks to fill this gap by offering a unified perspective on Long CoT. (1) We first distinguish Long CoT from Short CoT and introduce a novel taxonomy to categorize current reasoning paradigms. (2) Next, we explore the key characteristics of Long CoT: deep reasoning, extensive exploration, and feasible reflection, which enable models to handle more complex tasks and produce more efficient, coherent outcomes compared to the shallower Short CoT. (3) We then investigate key phenomena such as the emergence of Long CoT with these characteristics, including overthinking, and test-time scaling, offering insights into how these processes manifest in practice. (4) Finally, we identify significant research gaps and highlight promising future directions, including the integration of multi-modal reasoning, efficiency improvements, and enhanced knowledge frameworks. By providing a structured overview, this survey aims to inspire future research and further the development of logical reasoning in artificial intelligence.

Fine-tuning plays a crucial role in enabling pre-trained LLMs to evolve from general language comprehension to task-specific expertise. To preserve user data privacy, federated fine-tuning is often employed and has emerged as the de facto paradigm. However, federated fine-tuning is prohibitively inefficient due to the tension between LLM complexity and the resource constraint of end devices, incurring unaffordable fine-tuning overhead. Existing literature primarily utilizes parameter-efficient fine-tuning techniques to mitigate communication costs, yet computational and memory burdens continue to pose significant challenges for developers. This work proposes DropPEFT, an innovative federated PEFT framework that employs a novel stochastic transformer layer dropout method, enabling devices to deactivate a considerable fraction of LLMs layers during training, thereby eliminating the associated computational load and memory footprint. In DropPEFT, a key challenge is the proper configuration of dropout ratios for layers, as overhead and training performance are highly sensitive to this setting. To address this challenge, we adaptively assign optimal dropout-ratio configurations to devices through an exploration-exploitation strategy, achieving efficient and effective fine-tuning. Extensive experiments show that DropPEFT can achieve a 1.3-6.3\times speedup in model convergence and a 40%-67% reduction in memory footprint compared to state-of-the-art methods.

The rapid advancement of Large Multi-modal Models (LMMs) has enabled their application in scientific problem-solving, yet their fine-grained capabilities remain under-explored. In this paper, we introduce SciVerse, a multi-modal scientific evaluation benchmark to thoroughly assess LMMs across 5,735 test instances in five distinct versions. We aim to investigate three key dimensions of LMMs: scientific knowledge comprehension, multi-modal content interpretation, and Chain-of-Thought (CoT) reasoning. To unveil whether LMMs possess sufficient scientific expertise, we first transform each problem into three versions containing different levels of knowledge required for solving, i.e., Knowledge-free, -lite, and -rich. Then, to explore how LMMs interpret multi-modal scientific content, we annotate another two versions, i.e., Vision-rich and -only, marking more question information from texts to diagrams. Comparing the results of different versions, SciVerse systematically examines the professional knowledge stock and visual perception skills of LMMs in scientific domains. In addition, to rigorously assess CoT reasoning, we propose a new scientific CoT evaluation strategy, conducting a step-wise assessment on knowledge and logical errors in model outputs. Our extensive evaluation of different LMMs on SciVerse reveals critical limitations in their scientific proficiency and provides new insights into future developments. Project page: https://sciverse-cuhk.github.io

Time-series analysis is critical for a wide range of fields such as healthcare, finance, transportation, and energy, among many others. The practical applications often involve analyzing time-series data alongside contextual information in the form of natural language to support informed decisions. However, current time-series models are limited in their ability to perform reasoning that involves both time-series and their textual content. In this work, we address this gap by introducing \textit{Chat-TS}, a large language model (LLM) based framework, designed to support reasoning over time series and textual data. Unlike traditional models, Chat-TS integrates time-series tokens into LLMs' vocabulary, enhancing its reasoning ability over both modalities without compromising the core natural language capabilities, enabling practical analysis and reasoning across modalities. To support learning and evaluation in this setup, we contribute new datasets: the \textit{TS Instruct Training Dataset} which pairs diverse time-series data with relevant text instructions and responses for instruction tuning, the \textit{TS Instruct Question and Answer (QA) Gold Dataset} which provides multiple-choice questions designed to evaluate multimodal reasoning, and a \textit{TS Instruct Quantitative Probing Set} which contains a small subset of the TS Instruct QA tasks alongside math and decision-making questions for LLM evaluation. We designed a training strategy to preserve the inherent reasoning capabilities of LLMs while augmenting them for time-series reasoning. Experiments show that Chat-TS achieves state-of-the-art performance in multi-modal reasoning tasks by maintaining strong natural language proficiency while improving time-series reasoning. ~\footnote{To ensure replicability and facilitate future research, all models, datasets, and code will be available at [\texttt{Github-URL}].}