Recent advancements in Multimodal Large Language Models (MLLMs) have shown remarkable capabilities across various multimodal contexts. However, their application in robotic scenarios, particularly for long-horizon manipulation tasks, reveals significant limitations. These limitations arise from the current MLLMs lacking three essential robotic brain capabilities: Planning Capability, which involves decomposing complex manipulation instructions into manageable sub-tasks; Affordance Perception, the ability to recognize and interpret the affordances of interactive objects; and Trajectory Prediction, the foresight to anticipate the complete manipulation trajectory necessary for successful execution. To enhance the robotic brain's core capabilities from abstract to concrete, we introduce ShareRobot, a high-quality heterogeneous dataset that labels multi-dimensional information such as task planning, object affordance, and end-effector trajectory. ShareRobot's diversity and accuracy have been meticulously refined by three human annotators. Building on this dataset, we developed RoboBrain, an MLLM-based model that combines robotic and general multi-modal data, utilizes a multi-stage training strategy, and incorporates long videos and high-resolution images to improve its robotic manipulation capabilities. Extensive experiments demonstrate that RoboBrain achieves state-of-the-art performance across various robotic tasks, highlighting its potential to advance robotic brain capabilities.

Tuberculosis (TB) is the leading cause of death from an infectious disease globally, with the highest burden in low- and middle-income countries. In these regions, limited healthcare access and high patient-to-provider ratios impede effective patient support, communication, and treatment completion. To bridge this gap, we propose integrating a specialized Large Language Model into an efficacious digital adherence technology to augment interactive communication with treatment supporters. This AI-powered approach, operating within a human-in-the-loop framework, aims to enhance patient engagement and improve TB treatment outcomes.

Scaling long-context ability is essential for Large Language Models (LLMs). To amortize the memory consumption across multiple devices in long-context training, inter-data partitioning (a.k.a. Data Parallelism) and intra-data partitioning (a.k.a. Context Parallelism) are commonly used. Current training frameworks predominantly treat the two techniques as orthogonal, and establish static communication groups to organize the devices as a static mesh (e.g., a 2D mesh). However, the sequences for LLM training typically vary in lengths, no matter for texts, multi-modalities or reinforcement learning. The mismatch between data heterogeneity and static mesh causes redundant communication and imbalanced computation, degrading the training efficiency. In this work, we introduce ByteScale, an efficient, flexible, and scalable LLM training framework for large-scale mixed training of long and short sequences. The core of ByteScale is a novel parallelism strategy, namely Hybrid Data Parallelism (HDP), which unifies the inter- and intra-data partitioning with a dynamic mesh design. In particular, we build a communication optimizer, which eliminates the redundant communication for short sequences by data-aware sharding and dynamic communication, and further compresses the communication cost for long sequences by selective offloading. Besides, we also develop a balance scheduler to mitigate the imbalanced computation by parallelism-aware data assignment. We evaluate ByteScale with the model sizes ranging from 7B to 141B, context lengths from 256K to 2048K, on a production cluster with more than 12,000 GPUs. Experiment results show that ByteScale outperforms the state-of-the-art training system by up to 7.89x.

Chain of Thought (CoT) prompting has been shown to significantly improve the performance of large language models (LLMs), particularly in arithmetic and reasoning tasks, by instructing the model to produce intermediate reasoning steps. Despite the remarkable empirical success of CoT and its theoretical advantages in enhancing expressivity, the mechanisms underlying CoT training remain largely unexplored. In this paper, we study the training dynamics of transformers over a CoT objective on an in-context weight prediction task for linear regression. We prove that while a one-layer linear transformer without CoT can only implement a single step of gradient descent (GD) and fails to recover the ground-truth weight vector, a transformer with CoT prompting can learn to perform multi-step GD autoregressively, achieving near-exact recovery. Furthermore, we show that the trained transformer effectively generalizes on the unseen data. With our technique, we also show that looped transformers significantly improve final performance compared to transformers without looping in the in-context learning of linear regression. Empirically, we demonstrate that CoT prompting yields substantial performance improvements.

Recent research has shown that LLM performance on reasoning tasks can be enhanced by scaling test-time compute. One promising approach, particularly with decomposable problems, involves arranging intermediate solutions as a graph on which transformations are performed to explore the solution space. However, prior works rely on pre-determined, task-specific transformation schedules which are subject to a set of searched hyperparame-ters. In this work, we view thought graph transformations as actions in a Markov decision process, and implement policy agents to drive effective action policies for the underlying reasoning LLM agent. In particular, we investigate the ability for another LLM to act as a policy agent on thought graph environments and introduce ARIES, a multi-agent architecture for reasoning with LLMs. In ARIES, reasoning LLM agents solve decomposed subproblems, while policy LLM agents maintain visibility of the thought graph states, and dynamically adapt the problem-solving strategy. Through extensive experiments, we observe that using off-the-shelf LLMs as policy agents with no supervised fine-tuning (SFT) can yield up to 29% higher accuracy on HumanEval relative to static transformation schedules, as well as reducing inference costs by 35% and avoid any search requirements. We also conduct a thorough analysis of observed failure modes, highlighting that limitations on LLM sizes and the depth of problem decomposition can be seen as challenges to scaling LLM-guided reasoning. Prior works have shown that Large Language Models (LLMs) are subject to the emergence of abilities as their parameter count grows (Wei et al., 2022), which spurred significant interest in training increasingly larger models. However, recent work showed that under a fixed compute budget for training and inference, LLM performance on reasoning tasks can be enhanced by allocating a higher proportion of compute to inference rather than training (Snell et al., 2024). This shift towards inference-time compute scaling can be intuitively understood through the Dual Process Theory, which postulates the existence of two distinct modes of reasoning in humans - (1) a fast, intuitive mode and (2) a slow, deliberate mode (Evans & Frankish, 2009).

The integration of Environmental, Social, and Governance (ESG) factors into corporate decision-making is a fundamental aspect of sustainable finance. However, ensuring that business practices align with evolving regulatory frameworks remains a persistent challenge. AI-driven solutions for automatically assessing the alignment of sustainability reports and non-financial disclosures with specific ESG activities could greatly support this process. Y et, this task remains complex due to the limitations of general-purpose Large Language Models (LLMs) in domain-specific contexts and the scarcity of structured, high-quality datasets. In this paper, we investigate the ability of current-generation LLMs to identify text related to environmental activities. Furthermore, we demonstrate that their performance can be significantly enhanced through fine-tuning on a combination of original and synthetically generated data. T o this end, we introduce ESG-Activities, a benchmark dataset containing 1,325 labeled text segments classified according to the EU ESG taxonomy. Our experimental results show that fine-tuning on ESG-Activities significantly enhances classification accuracy, with open models such as Llama 7B and Gemma 7B outperforming large proprietary solutions in specific configurations. These findings have important implications for financial analysts, policymakers, and AI researchers seeking to enhance ESG transparency and compliance through advanced natural language processing techniques. N recent years, driven by the widespread adoption of the Sustainable Development Goals (SDGs), the European Union has introduced principles and regulations aimed at helping organizations integrate environmental, social, and governance (ESG) factors into their operations and strategic decision-making. These initiatives encourage businesses and investors to assess and improve their environmental impact, fostering a more sustainable approach to economic activity [1]. This resource enables companies to evaluate their activities in alignment with its criteria and report their performance in non-financial disclosures and sustainability reports.

Clinical cohort definition is crucial for patient recruitment and observational studies, yet translating inclusion/exclusion criteria into SQL queries remains challenging and manual. We present an automated system utilizing large language models that combines criteria parsing, two-level retrieval augmented generation with specialized knowledge bases, medical concept standardization, and SQL generation to retrieve patient cohorts with patient funnels. The system achieves 0.75 F1-score in cohort identification on EHR data, effectively capturing complex temporal and logical relationships. These results demonstrate the feasibility of automated cohort generation for epidemiological research.

The question of whether large language models (LLMs) possess Theory of Mind (ToM) -- often defined as the ability to reason about others' mental states -- has sparked significant scientific and public interest. However, the evidence as to whether LLMs possess ToM is mixed, and the recent growth in evaluations has not resulted in a convergence. Here, we take inspiration from cognitive science to re-evaluate the state of ToM evaluation in LLMs. We argue that a major reason for the disagreement on whether LLMs have ToM is a lack of clarity on whether models should be expected to match human behaviors, or the computations underlying those behaviors. We also highlight ways in which current evaluations may be deviating from "pure" measurements of ToM abilities, which also contributes to the confusion. We conclude by discussing several directions for future research, including the relationship between ToM and pragmatic communication, which could advance our understanding of artificial systems as well as human cognition.

Predicting the future trajectory of complex and rapidly evolving systems remains a significant challenge, particularly in domains where data is scarce or unreliable. This study introduces a novel approach to qualitative forecasting by leveraging Large Language Models to conduct Delphi studies. The methodology was applied to explore the future evolution of Generative Artificial Intelligence, revealing insights into key factors such as geopolitical tensions, economic disparities, regulatory frameworks, and ethical considerations. The results highlight how LLM-based Delphi studies can facilitate structured scenario analysis, capturing diverse perspectives while mitigating issues such as respondent fatigue. However, limitations emerge in terms of knowledge cutoffs, inherent biases, and sensitivity to initial conditions. While the approach provides an innovative means for structured foresight, this method could be also considered as a novel form of reasoning. further research is needed to refine its ability to manage heterogeneity, improve reliability, and integrate external data sources.

Large language models (LLMs) have shown impressive abilities in answering questions across various domains, but they often encounter hallucination issues on questions that require professional and up-to-date knowledge. To address this limitation, retrieval-augmented generation (RAG) techniques have been proposed, which retrieve relevant information from external sources to inform their responses. However, existing RAG methods typically focus on a single type of external data, such as vectorized text database or knowledge graphs, and cannot well handle real-world questions on semi-structured data containing both text and relational information. To bridge this gap, we introduce PASemiQA, a novel approach that jointly leverages text and relational information in semi-structured data to answer questions. PASemiQA first generates a plan to identify relevant text and relational information to answer the question in semi-structured data, and then uses an LLM agent to traverse the semi-structured data and extract necessary information. Our empirical results demonstrate the effectiveness of PASemiQA across different semi-structured datasets from various domains, showcasing its potential to improve the accuracy and reliability of question answering systems on semi-structured data.