W e assemble a large, domain - specialized clinical corpus and a clinician - validated reasoning set, and develop RareSeek - R1 via staged instruction tuning, chain - of - thought learning, and graph - grounded retrieval. Across multicenter EHR narratives and public benchmarks, RareSeek - R1 attains state - of - the - art accuracy, robust generalization, and stability under noisy or overlapping phenotypes. Augmented retrieval yields the largest gains when narratives pair with prioritized variants by resolving ambiguity and aligning candidates to mechanisms. Human studies show performance on par with experienced physicians and consistent gains in assistive use. Notably, transparent reasoning highlights decisive non - phenotypic evidence (median 23.1%, such as imaging, interventions, functional tests) underpinning many correct diagnoses. This work advances a narrative - first, knowledge - integrated reasoning paradigm that shortens the diagnostic odyssey and enables auditable, clinically translatable decision support.

Scientific idea generation and selection requires exploration following a target probability distribution. In contrast, current AI benchmarks have objectively correct answers, and training large language models (LLMs) via reinforcement learning against these benchmarks discourages probabilistic exploration. Here, we conducted systematic experiments requesting LLMs to produce outputs following simple probabilistic distributions, and found that all modern LLMs tested grossly fail to follow the distributions. For example, requesting a binary output of "1" 49% of the time produces an answer of "0" nearly 100% of the time. This step function-like behavior of near-exclusively generating the output with marginally highest probability even overrules even strong in-built LLM biases.

Detecting political bias in news media is a complex task that requires interpreting subtle linguistic and contextual cues. Although recent advances in Natural Language Processing (NLP) have enabled automatic bias classification, the extent to which large language models (LLMs) align with human judgment still remains relatively underexplored and not yet well understood. This study aims to present a comparative framework for evaluating the detection of political bias across human annotations and multiple LLMs, including GPT, BERT, RoBERTa, and FLAN. We construct a manually annotated dataset of news articles and assess annotation consistency, bias polarity, and inter-model agreement to quantify divergence between human and model perceptions of bias. Experimental results show that among traditional transformer-based models, RoBERTa achieves the highest alignment with human labels, whereas generative models such as GPT demonstrate the strongest overall agreement with human annotations in a zero-shot setting. Among all transformer-based baselines, our fine-tuned RoBERTa model acquired the highest accuracy and the strongest alignment with human-annotated labels. Our findings highlight systematic differences in how humans and LLMs perceive political slant, underscoring the need for hybrid evaluation frameworks that combine human interpretability with model scalability in automated media bias detection.

High quality summarization data remains scarce in under-represented languages. However, historical newspapers, made available through recent digitization efforts, offer an abundant source of untapped, naturally annotated data. In this work, we present a novel method for collecting naturally occurring summaries via Front-Page Teasers, where editors summarize full length articles. We show that this phenomenon is common across seven diverse languages and supports multi-document summarization. To scale data collection, we develop an automatic process, suited to varying linguistic resource levels. Finally, we apply this process to a Hebrew newspaper title, producing HEBTEASESUM, the first dedicated multi-document summarization dataset in Hebrew.

Abstract--T ask-oriented knowledge graphs (KGs) enable AIpowered learning assistant systems to automatically generate high-quality multiple-choice questions (MCQs). Y et converting unstructured educational materials, such as lecture notes and slides, into KGs that capture key pedagogical content remains difficult. We propose a framework for knowledge graph construction and refinement grounded in rate-distortion (RD) theory and optimal transport geometry. In the framework, lecture content is modeled as a metric-measure space, capturing semantic and relational structure, while candidate KGs are aligned using Fused Gromov-Wasserstein (FGW) couplings to quantify semantic distortion. The rate term, expressed via the size of KG, reflects complexity and compactness. Refinement operators (add, merge, split, remove, rewire) minimize the rate-distortion Lagrangian, yielding compact, information-preserving KGs. Our prototype applied to data science lectures yields interpretable RD curves and shows that MCQs generated from refined KGs consistently surpass those from raw notes on fifteen quality criteria. This study establishes a principled foundation for information-theoretic KG optimization in personalized and AI-assisted education. An AI-powered learning assistant (AILA) system [1] can automatically generate educational questions such as multiple choice questions (MCQs) from teaching materials including lecture notes and slides [2], [3]. Recent research demonstrates that integrating knowledge graphs (KGs) with large language models (LLMs) significantly improves the factual accuracy, explainability, and reasoning capabilities of LLM-powered answers [4], [5].

Enabling agents to learn from experience and generalize across diverse tasks without task-specific training remains a fundamental challenge in reinforcement learning and decision-making. While recent approaches have explored episodic memory (Reflexion), gradient-based prompt optimization (TextGrad),and hierarchical task decomposition independently, their potential for synergistic integration remains unexplored. We introduce ReflexGrad, a novel architecture that tightly couples three complementary mechanisms: (1) LLM-based hierarchical TODO decomposition for strategic planning, (2) history-aware causal reflection that analyzes recent action patterns to identify failure root causes and enable within-trial learning, and (3) gradient-based optimization for systematic improvement. Unlike prior work relying on few-shot demonstrations, our system achieves true zero-shot generalization through pure LLM semantic reasoning,requiring no task-specific examples, fine-tuning, or hardcoded similarity metrics. Evaluated on ALFWorld benchmark tasks, ReflexGrad demonstrates 67% zero-shot success rate on Trial 0 without any prior task experience or demonstrations, establishing effective performance on first exposure. Through empirical analysis, we identify the architectural mechanisms underlying stable convergence (zero action loops) and effective cross-task transfer (67% to 78% improvement).Our work demonstrates that synergistic integration of complementary learning mechanisms enables robust zero-shot generalization that approaches few-shot baselines from prior work.

Robots can adapt to user preferences by learning reward functions from demonstrations, but with limited data, reward models often overfit to spurious correlations and fail to generalize. This happens because demonstrations show robots how to do a task but not what matters for that task, causing the model to focus on irrelevant state details. Natural language can more directly specify what the robot should focus on, and, in principle, disambiguate between many reward functions consistent with the demonstrations. However, existing language-conditioned reward learning methods typically treat instructions as simple conditioning signals, without fully exploiting their potential to resolve ambiguity. Moreover, real instructions are often ambiguous themselves, so naive conditioning is unreliable. Our key insight is that these two input types carry complementary information: demonstrations show how to act, while language specifies what is important. We propose Masked Inverse Reinforcement Learning (Masked IRL), a framework that uses large language models (LLMs) to combine the strengths of both input types. Masked IRL infers state-relevance masks from language instructions and enforces invariance to irrelevant state components. When instructions are ambiguous, it uses LLM reasoning to clarify them in the context of the demonstrations. In simulation and on a real robot, Masked IRL outperforms prior language-conditioned IRL methods by up to 15% while using up to 4.7 times less data, demonstrating improved sample-efficiency, generalization, and robustness to ambiguous language. Project page: https://MIT-CLEAR-Lab.github.io/Masked-IRL and Code: https://github.com/MIT-CLEAR-Lab/Masked-IRL

With Retrieval Augmented Generation (RAG) becoming more and more prominent in generative AI solutions, there is an emerging need for systematically evaluating their effectiveness. We introduce the LiveRAG benchmark, a publicly available dataset of 895 synthetic questions and answers designed to support systematic evaluation of RAG-based Q&A systems. This synthetic benchmark is derived from the one used during the SIGIR'2025 LiveRAG Challenge, where competitors were evaluated under strict time constraints. It is augmented with information that was not made available to competitors during the Challenge, such as the ground-truth answers, together with their associated supporting claims which were used for evaluating competitors' answers. In addition, each question is associated with estimated difficulty and discriminability scores, derived from applying an Item Response Theory model to competitors' responses. Our analysis highlights the benchmark's questions diversity, the wide range of their difficulty levels, and their usefulness in differentiating between system capabilities. The LiveRAG benchmark will hopefully help the community advance RAG research, conduct systematic evaluation, and develop more robust Q&A systems.

The growth of million-token LLMs exposes the scalability limits of inference systems, where the KVCache dominates memory usage and data transfer overhead. Recent offloading systems migrate the KVCache to CPU memory and incorporate top-k attention to reduce the volume of data transferred from the CPU, while further applying system-level optimizations such as on-GPU caching and prefetching to lower transfer overhead. However, they overlook the CPU bottleneck in three aspects: (1) substantial overhead of fine-grained dynamic cache management performed on the CPU side, (2) significant transfer overhead from poor PCIe bandwidth utilization caused by heavy gathering operations at the CPU side, and (3) GPU runtime bubbles introduced by coarse-grained CPU-centric synchronization. To address these challenges, we propose CLO, a CPU-light KVCache offloading system via algorithm-system co-design. CLO features: (1) a coarse-grained head-wise approximate on-GPU caching strategy with negligible cache management cost, (2) seamless combination of data prefetching and on-GPU persistent caching for lower transfer overhead, (3) a zero-copy transfer engine to fully exploit PCIe bandwidth, and a GPU-centric synchronization method to eliminate GPU stalls. Evaluation on two widely-used LLMs demonstrates that CLO achieves comparable accuracy to state-of-the-art systems, while substantially minimizing CPU overhead, fully utilizing PCIe bandwidth, thus improving decoding throughput by 9.3%-66.6%. Our results highlight that algorithm-system co-design is essential for memory-constrained LLM inference on modern GPU platforms. We open source CLO at https://github.com/CommediaJW/CLO.

Large Language Models (LLMs) are increasingly being explored for building Agents capable of active environmental interaction (e.g., via tool use) to solve complex problems. Reinforcement Learning (RL) is considered a key technology with significant potential for training such Agents; however, the effective application of RL to LLM Agents is still in its nascent stages and faces considerable challenges. Currently, this emerging field lacks in-depth exploration into RL approaches specifically tailored for the LLM Agent context, alongside a scarcity of flexible and easily extensible training frameworks designed for this purpose. To help advance this area, this paper first revisits and clarifies Reinforcement Learning methodologies for LLM Agents by systematically extending the Markov Decision Process (MDP) framework to comprehensively define the key components of an LLM Agent. Secondly, we introduce Agent-R1, a modular, flexible, and user-friendly training framework for RL-based LLM Agents, designed for straightforward adaptation across diverse task scenarios and interactive environments. We conducted experiments on Multihop QA benchmark tasks, providing initial validation for the effectiveness of our proposed methods and framework.