Related papers: Chain of Unit-Physics: A Primitive-Centric Approac…
Training on verifiable symbolic data is a promising way to expand the reasoning frontier of language models beyond what standard pre-training corpora provide. Yet existing procedural generators often rely on fixed puzzles or templates and…
The automated generation of agentic workflows is a promising frontier for enabling large language models (LLMs) to solve complex tasks. However, our investigation reveals that the robustness of agentic workflow remains a critical,…
Recent advances in code generation models have unlocked unprecedented opportunities for automating feature engineering, yet their adoption in real-world ML teams remains constrained by critical challenges: (i) the scarcity of datasets…
Large language models (LLMs) and high-capacity encoders have advanced zero and few-shot classification, but their inference cost and latency limit practical deployment. We propose training lightweight text classifiers using dynamically…
The emergence of large language models has enabled sophisticated multi-agent systems, yet coordinating their reasoning capabilities through prompt engineering remains challenging. We present a theoretically-grounded framework for dynamic…
We present the first language-model-driven agentic artificial intelligence (AI) system to autonomously execute multi-stage physics experiments on a production synchrotron light source. Implemented at the Advanced Light Source particle…
Computer-use agents face a fundamental limitation. They rely exclusively on primitive GUI actions (click, type, scroll), creating brittle execution chains prone to cascading failures. While API-driven agents harness rich capabilities…
Robotic laboratories play a critical role in autonomous scientific discovery by enabling scalable, continuous experimental execution. Recent vision-language-action (VLA) models offer a promising foundation for robotic laboratories. However,…
Evaluating outputs of large language models (LLMs) is challenging, requiring making -- and making sense of -- many responses. Yet tools that go beyond basic prompting tend to require knowledge of programming APIs, focus on narrow domains,…
Large Language Models (LLMs) have demonstrated potential in code generation, yet they struggle with the multi-step, stateful reasoning required for offensive cybersecurity operations. Existing research often relies on static benchmarks that…
Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…
Language models are revolutionizing the biochemistry domain, assisting scientists in drug design and chemical synthesis with high efficiency. Yet current approaches struggle between small language models prone to hallucination and limited…
In industrial control systems, the generation and verification of Programmable Logic Controller (PLC) code are critical for ensuring operational efficiency and safety. While Large Language Models (LLMs) have made strides in automated code…
Scientific texts often convey authority due to their technical language and complex data. However, this complexity can sometimes lead to the spread of misinformation. Non-experts are particularly susceptible to misleading claims based on…
As large reasoning models (LRMs) grow more capable, chain-of-thought (CoT) reasoning introduces new safety challenges. Existing SFT-based safety alignment studies dominantly focused on filtering prompts with safe, high-quality responses,…
Despite the growing application of Large Language Models (LLMs) to theoretical physics, there is little academic exploration into how domain-specific physics reasoning ability develops while training these models. To investigate this, we…
PDEs are central to scientific and engineering modeling, yet designing accurate numerical solvers typically requires substantial mathematical expertise and manual tuning. Recent neural network-based approaches improve flexibility but often…
With the widespread adoption of large language models (LLMs) in natural language processing, prompt engineering and retrieval-augmented generation (RAG) have become mainstream to enhance LLMs' performance on complex tasks. However, LLMs…
Chain-of-thought prompting has demonstrated remarkable performance on various natural language reasoning tasks. However, it tends to perform poorly on tasks which requires solving problems harder than the exemplars shown in the prompts. To…
Agentic coding systems increasingly use large language models (LLMs) for software engineering tasks such as debugging, root cause analysis, and code review. However, many existing systems encode task logic, execution flow, and output…