One approach to this question is to compare the cognitive dynamics of humans and large language models (LLMs). However, such a comparison requires a method to quantitatively analyze AI cognitive behavior under controlled conditions. While anecdotal observations suggest that certain prompts can dramatically change LLM behavior, these observations have remained largely qualitative. Here, we propose a two - part framework to investigate this phenomenon: a Transition - Inducing Prompt (TIP) that triggers a rapid shift in LLM responsiveness, and a Transition Quantifying Prompt (TQP) that evaluates this change using a separate LLM. Through c ontrolled experiments, we examined how LLMs react to prompts embedding two semantically distant concepts (e.g., mathematical aperiodicity and traditional crafts) - either fused together or presented separately - by changing their linguistic quality and affective tone. Whereas humans tend to experience heightened engagement when such concepts are meaningfully blended producing a novel c o ncept - a form of conceptual fusion - current LLMs showed no significant difference in responsiveness between semantically fused and non - fused prompts. This suggests that LLMs may not yet replicate the conceptual integration processes seen in human intuition. Our method enables fine - grained, reproducible measurement of cognitive responsiveness, and may help illuminate key differences in how intuition and conceptual leaps emerge in artificial versus human minds. Keywords: Human - AI collaboration, Cognitive Phase Transition, Transition - Inducing Prompts, Transition Quantifying Prompts, Prompt Engineering, Conceptual fusion Highlights: 1. Collaborative research between a human and an AI reveals both parallels and gaps in their cognitive processes.

Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning, which limits their accessibility. To address this, we introduce Trace-of-Thought Prompting, a novel framework designed to distill critical reasoning capabilities from high-resource teacher models (over 8 billion parameters) to low-resource student models (up to 8 billion parameters). This approach leverages problem decomposition to enhance interpretability and facilitate human-in-the-loop interventions. Empirical evaluations on the GSM8K and MATH datasets show that student models achieve accuracy gains of up to 113% on GSM8K and 21% on MATH, with significant improvements particularly notable in smaller models like Llama 2 and Zephyr. Our results suggest a promising pathway for open-source, low-resource models to eventually serve both as both students and teachers, potentially reducing our reliance on high-resource, proprietary models.

As large language models (LLMs) evolve into tool-using agents, the ability to browse the web in real-time has become a critical yardstick for measuring their reasoning and retrieval competence. Existing benchmarks such as BrowseComp concentrate on English and overlook the linguistic, infrastructural, and censorship-related complexities of other major information ecosystems -- most notably Chinese. To address this gap, we introduce BrowseComp-ZH, a high-difficulty benchmark purpose-built to comprehensively evaluate LLM agents on the Chinese web. BrowseComp-ZH consists of 289 multi-hop questions spanning 11 diverse domains. Each question is reverse-engineered from a short, objective, and easily verifiable answer (e.g., a date, number, or proper noun). A two-stage quality control protocol is applied to strive for high question difficulty and answer uniqueness. We benchmark over 20 state-of-the-art language models and agentic search systems on our proposed BrowseComp-ZH. Despite their strong conversational and retrieval capabilities, most models struggle severely: a large number achieve accuracy rates below 10%, and only a handful exceed 20%. Even the best-performing system, OpenAI's DeepResearch, reaches just 42.9%. These results demonstrate the considerable difficulty of BrowseComp-ZH, where success demands not only effective retrieval strategies, but also sophisticated reasoning and information reconciliation -- capabilities that current models still struggle to master. Our dataset, construction guidelines, and benchmark results have been publicly released at https://github.com/PALIN2018/BrowseComp-ZH.

Large language models (LLMs) have transformed code generation, yet their application in hardware design produces gate counts 38\%--1075\% higher than human designs. We present CircuitMind, a multi-agent framework that achieves human-competitive efficiency through three key innovations: syntax locking (constraining generation to basic logic gates), retrieval-augmented generation (enabling knowledge-driven design), and dual-reward optimization (balancing correctness with efficiency). To evaluate our approach, we introduce TC-Bench, the first gate-level benchmark harnessing collective intelligence from the TuringComplete ecosystem -- a competitive circuit design platform with hundreds of thousands of players. Experiments show CircuitMind enables 55.6\% of model implementations to match or exceed top-tier human experts in composite efficiency metrics. Most remarkably, our framework elevates the 14B Phi-4 model to outperform both GPT-4o mini and Gemini 2.0 Flash, achieving efficiency comparable to the top 25\% of human experts without requiring specialized training. These innovations establish a new paradigm for hardware optimization where collaborative AI systems leverage collective human expertise to achieve optimal circuit designs. Our model, data, and code are open-source at https://github.com/BUAA-CLab/CircuitMind.

Large Language Models (LLMs) have advanced Verilog code generation significantly, yet face challenges in data quality, reasoning capabilities, and computational efficiency. This paper presents ReasoningV, a novel model employing a hybrid reasoning strategy that integrates trained intrinsic capabilities with dynamic inference adaptation for Verilog code generation. Our framework introduces three complementary innovations: (1) ReasoningV-5K, a high-quality dataset of 5,000 functionally verified instances with reasoning paths created through multi-dimensional filtering of PyraNet samples; (2) a two-stage training approach combining parameter-efficient fine-tuning for foundational knowledge with full-parameter optimization for enhanced reasoning; and (3) an adaptive reasoning mechanism that dynamically adjusts reasoning depth based on problem complexity, reducing token consumption by up to 75\% while preserving performance. Experimental results demonstrate ReasoningV's effectiveness with a pass@1 accuracy of 57.8\% on VerilogEval-human, achieving performance competitive with leading commercial models like Gemini-2.0-flash (59.5\%) and exceeding the previous best open-source model by 10.4 percentage points. ReasoningV offers a more reliable and accessible pathway for advancing AI-driven hardware design automation, with our model, data, and code available at https://github.com/BUAA-CLab/ReasoningV.

Reinforcement finetuning (RFT) has shown great potential for enhancing the mathematical reasoning capabilities of large language models (LLMs), but it is often sample- and compute-inefficient, requiring extensive training. In this work, we introduce AdaRFT (Adaptive Curriculum Reinforcement Finetuning), a method that significantly improves both the efficiency and final accuracy of RFT through adaptive curriculum learning. AdaRFT dynamically adjusts the difficulty of training problems based on the model's recent reward signals, ensuring that the model consistently trains on tasks that are challenging but solvable. This adaptive sampling strategy accelerates learning by maintaining an optimal difficulty range, avoiding wasted computation on problems that are too easy or too hard. AdaRFT requires only a lightweight extension to standard RFT algorithms like Proximal Policy Optimization (PPO), without modifying the reward function or model architecture. Experiments on competition-level math datasets-including AMC, AIME, and IMO-style problems-demonstrate that AdaRFT significantly improves both training efficiency and reasoning performance. We evaluate AdaRFT across multiple data distributions and model sizes, showing that it reduces training time by up to 2x and improves accuracy by a considerable margin, offering a more scalable and effective RFT framework.

Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT). In this work, we revisit the traditional Policy Gradient (PG) mechanism and propose a minimalist RL approach termed Group Policy Gradient (GPG). Unlike conventional methods, GPG directly optimize the original RL objective, thus obviating the need for surrogate loss functions. By eliminating the critic and reference models, avoiding KL divergence constraints, and addressing the advantage and gradient estimation bias, our approach significantly simplifies the training process compared to Group Relative Policy Optimization (GRPO). Our approach achieves superior performance without relying on auxiliary techniques or adjustments. As illustrated in Figure 1, extensive experiments demonstrate that our method not only reduces computational costs but also consistently outperforms GRPO across various unimodal and multimodal tasks. Our code is available at https://github.com/AMAP-ML/GPG.

Current molecular understanding approaches predominantly focus on the descriptive aspect of human perception, providing broad, topic-level insights. However, the referential aspect -- linking molecular concepts to specific structural components -- remains largely unexplored. To address this gap, we propose a molecular grounding benchmark designed to evaluate a model's referential abilities. We align molecular grounding with established conventions in NLP, cheminformatics, and molecular science, showcasing the potential of NLP techniques to advance molecular understanding within the AI for Science movement. Furthermore, we constructed the largest molecular understanding benchmark to date, comprising 117k QA pairs, and developed a multi-agent grounding prototype as proof of concept. This system outperforms existing models, including GPT-4o, and its grounding outputs have been integrated to enhance traditional tasks such as molecular captioning and ATC (Anatomical, Therapeutic, Chemical) classification.

At the start of April, an influx of action figure started appearing on social media sites including LinkedIn and X. Each figure depicted the person who had created it with uncanny accuracy, complete with personalized accessories such as reusable coffee cups, yoga mats, and headphones. All this is possible because of OpenAI's new GPT-4o-powered image generator, which supercharges ChatGPT's ability to edit pictures, render text, and more. OpenAI's ChatGPT image generator can also create pictures in the style of Japanese animated film company Studio Ghibli--a trend that quickly went viral, too. The images are fun and easy to make--all you need is a free ChatGPT account and a photo.

Robots equipped with the π0.5 AI model were tested in homes they had never seen before An AI enabling robots to do chores like making the bed or cleaning up spills in homes it has never seen before could allow many more robots to become generally useful, its creators say. Large language models (LLMs) like ChatGPT have improved robots' ability to carry out spoken requests. However, most robots work well only in environments in which they have been trained; their performance quality sharply falls when confronted with new and unfamiliar spaces.