Scientific experimentation, a cornerstone of human progress, demands rigor in reliability, methodical control, and interpretability to yield meaningful results. Despite the growing capabilities of large language models (LLMs) in automating different aspects of the scientific process, automating rigorous experimentation remains a significant challenge. To address this gap, we propose Curie, an AI agent framework designed to embed rigor into the experimentation process through three key components: an intra-agent rigor module to enhance reliability, an inter-agent rigor module to maintain methodical control, and an experiment knowledge module to enhance interpretability. To evaluate Curie, we design a novel experimental benchmark composed of 46 questions across four computer science domains, derived from influential research papers, and widely adopted open-source projects. Compared to the strongest baseline tested, we achieve a 3.4$\times$ improvement in correctly answering experimental questions. Curie is open-sourced at https://github.com/Just-Curieous/Curie.

A significant and growing number of published scientific articles is found to involve fraudulent practices, posing a serious threat to the credibility and safety of research in fields such as medicine. We propose Pub-Guard-LLM, the first large language model-based system tailored to fraud detection of biomedical scientific articles. We provide three application modes for deploying Pub-Guard-LLM: vanilla reasoning, retrieval-augmented generation, and multi-agent debate. Each mode allows for textual explanations of predictions. To assess the performance of our system, we introduce an open-source benchmark, PubMed Retraction, comprising over 11K real-world biomedical articles, including metadata and retraction labels. We show that, across all modes, Pub-Guard-LLM consistently surpasses the performance of various baselines and provides more reliable explanations, namely explanations which are deemed more relevant and coherent than those generated by the baselines when evaluated by multiple assessment methods. By enhancing both detection performance and explainability in scientific fraud detection, Pub-Guard-LLM contributes to safeguarding research integrity with a novel, effective, open-source tool.

Despite recent advances in understanding the capabilities and limits of generative artificial intelligence (GenAI) models, we are just beginning to understand their capacity to assess and reason about the veracity of content. We evaluate multiple GenAI models across tasks that involve the rating of, and perceived reasoning about, the credibility of information. The information in our experiments comes from content that subnational U.S. politicians post to Facebook. We find that GPT-4o, one of the most used AI models in consumer applications, outperforms other models, but all models exhibit only moderate agreement with human coders. Importantly, even when GenAI models accurately identify low-credibility content, their reasoning relies heavily on linguistic features and ``hard'' criteria, such as the level of detail, source reliability, and language formality, rather than an understanding of veracity. We also assess the effectiveness of summarized versus full content inputs, finding that summarized content holds promise for improving efficiency without sacrificing accuracy. While GenAI has the potential to support human fact-checkers in scaling misinformation detection, our results caution against relying solely on these models.

The reasoning abilities are one of the most enigmatic and captivating aspects of large language models (LLMs). Numerous studies are dedicated to exploring and expanding the boundaries of this reasoning capability. However, tasks that embody both reasoning and recall characteristics are often overlooked. In this paper, we introduce such a novel task, code reasoning, to provide a new perspective for the reasoning abilities of LLMs. We summarize three meta-benchmarks based on established forms of logical reasoning, and instantiate these into eight specific benchmark tasks. Our testing on these benchmarks reveals that LLMs continue to struggle with identifying satisfactory reasoning pathways. Additionally, we present a new pathway exploration pipeline inspired by human intricate problem-solving methods. This Reflective Hypothesis Decomposition and Amendment (RHDA) pipeline consists of the following iterative steps: (1) Proposing potential hypotheses based on observations and decomposing them; (2) Utilizing tools to validate hypotheses and reflection outcomes; (3) Revising hypothesis in light of observations. Our approach effectively mitigates logical chain collapses arising from forgetting or hallucination issues in multi-step reasoning, resulting in performance gains of up to $3\times$. Finally, we expanded this pipeline by applying it to simulate complex household tasks in real-world scenarios, specifically in VirtualHome, enhancing the handling of failure cases. We release our code and all of results at https://github.com/TnTWoW/code_reasoning.

Large language models (LLMs) have demonstrated strong effectiveness and robustness while fine-tuned as dense retrievers. However, their large parameter size brings significant inference time computational challenges, including high encoding costs for large-scale corpora and increased query latency, limiting their practical deployment. While smaller retrievers offer better efficiency, they often fail to generalize effectively with limited supervised fine-tuning data. In this work, we introduce DRAMA, a training framework that leverages LLMs to train smaller generalizable dense retrievers. In particular, we adopt pruned LLMs as the backbone and train on diverse LLM-augmented data in a single-stage contrastive learning setup. Experiments show that DRAMA offers better multilingual and long-context capabilities than traditional encoder-based retrievers, and achieves strong performance across multiple tasks and languages. These highlight the potential of connecting the training of smaller retrievers with the growing advancements in LLMs, bridging the gap between efficiency and generalization.

--Detecting design pattern instances in unfamiliar codebases remains a challenging yet essential task for improving software quality and maintainability. Traditional static analysis tools often struggle with the complexity, variability, and lack of explicit annotations that characterize real-world pattern implementations. In this paper, we present a novel approach leveraging Large Language Models to automatically identify design pattern instances across diverse codebases. Our method focuses on recognizing the roles classes play within the pattern instances. By providing clearer insights into software structure and intent, this research aims to support developers, improve comprehension, and streamline tasks such as refactoring, maintenance, and adherence to best practices. Identifying design pattern instances in code is a valuable goal as it enables a deeper understanding of the structural and behavioral principles underlying software systems. By uncovering these patterns, developers and other stakeholders can gain insights into code quality, maintainability, and adherence to best practices, even in unfamiliar code bases. Automating this process can significantly reduce the time and effort required for code comprehension, facilitate knowledge transfer among teams, and improve software evolution and refactoring efforts.

Large Language Models (LLMs) have the potential for substantial common sense reasoning. However, these capabilities are often emergent in larger models. This means smaller models that can be run locally are less helpful and capable with respect to certain reasoning tasks. To meet our problem space requirements, we fine-tune smaller LLMs to disaster domains, as these domains involve complex and low-frequency physical common sense knowledge. We introduce a pipeline to create Field Ready Instruction Decoding Agent (FRIDA) models, where domain experts and linguists combine their knowledge to make high-quality seed data that is used to generate synthetic data for fine-tuning. We create a set of 130 seed instructions for synthetic generation, a synthetic dataset of 25000 instructions, and 119 evaluation instructions relating to both general and earthquake-specific object affordances. We fine-tune several LLaMa and Mistral instruction-tuned models and find that FRIDA models outperform their base models at a variety of sizes. We then run an ablation study to understand which kinds of synthetic data most affect performance and find that training physical state and object function common sense knowledge alone improves over FRIDA models trained on all data. We conclude that the FRIDA pipeline is capable of instilling general common sense, but needs to be augmented with information retrieval for specific domain knowledge.

The recent DeepSeek-R1 release has demonstrated the immense potential of reinforcement learning (RL) in enhancing the general reasoning capabilities of large language models (LLMs). While DeepSeek-R1 and other follow-up work primarily focus on applying RL to competitive coding and math problems, this paper introduces SWE-RL, the first approach to scale RL-based LLM reasoning for real-world software engineering. Leveraging a lightweight rule-based reward (e.g., the similarity score between ground-truth and LLM-generated solutions), SWE-RL enables LLMs to autonomously recover a developer's reasoning processes and solutions by learning from extensive open-source software evolution data -- the record of a software's entire lifecycle, including its code snapshots, code changes, and events such as issues and pull requests. Trained on top of Llama 3, our resulting reasoning model, Llama3-SWE-RL-70B, achieves a 41.0% solve rate on SWE-bench Verified -- a human-verified collection of real-world GitHub issues. To our knowledge, this is the best performance reported for medium-sized (<100B) LLMs to date, even comparable to leading proprietary LLMs like GPT-4o. Surprisingly, despite performing RL solely on software evolution data, Llama3-SWE-RL has even emerged with generalized reasoning skills. For example, it shows improved results on five out-of-domain tasks, namely, function coding, library use, code reasoning, mathematics, and general language understanding, whereas a supervised-finetuning baseline even leads to performance degradation on average. Overall, SWE-RL opens up a new direction to improve the reasoning capabilities of LLMs through reinforcement learning on massive software engineering data.

PDF documents have the potential to provide trillions of novel, high-quality tokens for training language models. However, these documents come in a diversity of types with differing formats and visual layouts that pose a challenge when attempting to extract and faithfully represent the underlying content for language model use. We present olmOCR, an open-source Python toolkit for processing PDFs into clean, linearized plain text in natural reading order while preserving structured content like sections, tables, lists, equations, and more. Our toolkit runs a fine-tuned 7B vision language model (VLM) trained on a sample of 260,000 pages from over 100,000 crawled PDFs with diverse properties, including graphics, handwritten text and poor quality scans. olmOCR is optimized for large-scale batch processing, able to scale flexibly to different hardware setups and convert a million PDF pages for only $190 USD. We release all components of olmOCR including VLM weights, data and training code, as well as inference code built on serving frameworks including vLLM and SGLang.

Leveraging multiple large language models (LLMs) to build collaborative multi-agentic workflows has demonstrated significant potential. However, most previous studies focus on prompting the out-of-the-box LLMs, relying on their innate capability for collaboration, which may not improve LLMs' performance as shown recently. In this paper, we introduce a new post-training paradigm MAPoRL (Multi-Agent Post-co-training for collaborative LLMs with Reinforcement Learning), to explicitly elicit the collaborative behaviors and further unleash the power of multi-agentic LLM frameworks. In MAPoRL, multiple LLMs first generate their own responses independently and engage in a multi-turn discussion to collaboratively improve the final answer. In the end, a MAPoRL verifier evaluates both the answer and the discussion, by assigning a score that verifies the correctness of the answer, while adding incentives to encourage corrective and persuasive discussions. The score serves as the co-training reward, and is then maximized through multi-agent RL. Unlike existing LLM post-training paradigms, MAPoRL advocates the co-training of multiple LLMs together using RL for better generalization. Accompanied by analytical insights, our experiments demonstrate that training individual LLMs alone is insufficient to induce effective collaboration. In contrast, multi-agent co-training can boost the collaboration performance across benchmarks, with generalization to unseen domains.