In this paper, we propose a novel, automatic tree-based evaluation metric for LLM-generated step-by-step assembly instructions, that more accurately reflects spatiotemporal aspects of construction than traditional metrics such as BLEU and BERT similarity scores. We apply our proposed metric to the domain of sewing instructions, and show that our metric better correlates with manually-annotated error counts as well as human quality ratings, demonstrating our metric's superiority for evaluating the spatiotemporal soundness of sewing instructions. Further experiments show that our metric is more robust than traditional approaches against artificially-constructed counterfactual examples that are specifically constructed to confound metrics that rely on textual similarity.

Test-time Scaling (TTS) has been demonstrated to significantly enhance the reasoning capabilities of Large Language Models (LLMs) during the inference phase without altering model parameters. However, existing TTS methods are largely independent, implying that LLMs have not yet evolved to progressively learn how to scale more effectively. With the objective of evolving LLMs to learn "how to scale test-time computation," we propose LatentEvolve, a self-evolving latent TTS framework inspired by the complementary learning system (CLS) theory. Analogous to the human brain's dual system of a fast-recall hippocampus and a slow-consolidating neocortex, LatentEvolve comprises two evolutionary components: daytime scaling, which rapidly retrieves historical latent representations to better guide current LLM reasoning; and nighttime scaling, which integrates past latent optimizations in a manner akin to the human brain's consolidation of experiences during sleep. The alternation of daytime and nighttime processes facilitates a fast and slow evolution of LLM TTS, mirroring human cognitive dynamics in a fully unsupervised manner. Extensive experiments across eight benchmarks and five model backbones demonstrate that our LatentEvolve surpasses state-of-the-art TTS methods such as LatentSeek and TTRL by up to 13.33% and exhibits exceptional cross-domain and cross-backbone generalization. Much of this success in recent years has been driven by training-time scaling, wherein increasing the volume of training data and parameters consistently yields performance improvements (Kaplan et al., 2020; Aghajanyan et al., 2023). However, the pace of this scaling, particularly in terms of pre-training scale, has begun to slow, constrained by its resource-intensive nature and the depletion of high-quality training data (Villalobos et al., 2022; Zhou et al., 2025).

Large Language Models (LLMs) often generate incorrect or unsupported content, known as hallucinations. Existing detection methods rely on heuristics or simple models over isolated computational traces such as activations, or attention maps. We unify these signals by representing them as attributed graphs, where tokens are nodes, edges follow attentional flows, and both carry features from attention scores and activations. Our approach, CHARM, casts hallucination detection as a graph learning task and tackles it by applying GNNs over the above attributed graphs. We show that CHARM provably subsumes prior attention-based heuristics and, experimentally, it consistently outperforms other leading approaches across diverse benchmarks. Our results shed light on the relevant role played by the graph structure and on the benefits of combining computational traces, whilst showing CHARM exhibits promising zero-shot performance on cross-dataset transfer.

Despite remarkable advances, large language models often fail at compositional reasoning tasks, a phenomenon exemplified by the ``curse of two-hop reasoning''. This paper introduces the Identity Bridge, a simple yet powerful mechanism that resolves this compositionality gap by supervising the model on a zero-hop identity task. We demonstrate empirically that this addition enables models to successfully perform out-of-distribution two-hop reasoning, a task they otherwise completely fail. To explain this phenomenon, we provide a theoretical analysis using a simplified Emb-MLP model, proving that identity supervision reshapes the model's latent geometry. We show this alignment is induced by an implicit nuclear-norm regularization during optimization, which favors low-rank solutions that share structure across tasks. For complex tasks, we use small initialization or weight decay to enhance the regularization effect, which enhances the latent space alignment effect and slows down the generalization decay. Finally, we extend our investigation to large-scale models, observing that they still achieve two-hop reasoning through the latent memory, which provides crucial inspiration for enhancing their implicit reasoning abilities.

Large Language Models (LLMs) are typically evaluated through general or domain-specific benchmarks testing capabilities that often lack grounding in the lived realities of end users. Critical domains such as healthcare require evaluations that extend beyond artificial or simulated tasks to reflect the everyday needs, cultural practices, and nuanced contexts of communities. We propose Samiksha, a community-driven evaluation pipeline co-created with civil-society organizations (CSOs) and community members. Our approach enables scalable, automated benchmarking through a culturally aware, community-driven pipeline in which community feedback informs what to evaluate, how the benchmark is built, and how outputs are scored. We demonstrate this approach in the health domain in India. Our analysis highlights how current multilingual LLMs address nuanced community health queries, while also offering a scalable pathway for contextually grounded and inclusive LLM evaluation.

The explosive growth of large language models (LLMs) has created a vast but opaque landscape: millions of models exist, yet their evolutionary relationships through fine-tuning, distillation, or adaptation are often undocumented or unclear, complicating LLM management. Existing methods are limited by task specificity, fixed model sets, or strict assumptions about tokenizers or architectures. Inspired by biological DNA, we address these limitations by mathematically defining LLM DNA as a low-dimensional, bi-Lipschitz representation of functional behavior. We prove that LLM DNA satisfies inheritance and genetic determinism properties and establish the existence of DNA. Building on this theory, we derive a general, scalable, training-free pipeline for DNA extraction. In experiments across 305 LLMs, DNA aligns with prior studies on limited subsets and achieves superior or competitive performance on specific tasks. Beyond these tasks, DNA comparisons uncover previously undocumented relationships among LLMs. We further construct the evolutionary tree of LLMs using phylogenetic algorithms, which align with shifts from encoder-decoder to decoder-only architectures, reflect temporal progression, and reveal distinct evolutionary speeds across LLM families. The proliferation of large language models (LLMs) (Zhao et al., 2023) has produced a vast and complex landscape of models.

As Large Language Models (LLMs) achieve remarkable success across a wide range of applications, such as chatbots and code copilots, concerns surrounding the generation of harmful content have come increasingly into focus. Despite significant advances in aligning LLMs with safety and ethical standards, adversarial prompts can still be crafted to elicit undesirable responses. Existing mitigation strategies are predominantly based on post-hoc filtering, which introduces substantial latency or computational overhead, and is incompatible with token-level streaming generation. In this work, we introduce Self-Sanitize, a novel LLM-driven mitigation framework inspired by cognitive psychology, which emulates human self-monitor and self-repair behaviors during conversations. Self-Sanitize comprises a lightweight Self-Monitor module that continuously inspects high-level intentions within the LLM at the token level via representation engineering, and a Self-Repair module that performs in-place correction of harmful content without initiating separate review dialogues. This design allows for real-time streaming monitoring and seamless repair, with negligible impact on latency and resource utilization. Given that privacy-invasive content has often been insufficiently focused in previous studies, we perform extensive experiments on four LLMs across three privacy leakage scenarios. The results demonstrate that Self-Sanitize achieves superior mitigation performance with minimal overhead and without degrading the utility of LLMs, offering a practical and robust solution for safer LLM deployments.

The paradigm of Next Token Prediction (NTP) has driven the unprecedented success of Large Language Models (LLMs), but is also the source of their most persistent weaknesses such as poor long-term planning, error accumulation, and computational inefficiency. Acknowledging the growing interest in exploring alternatives to NTP, the survey describes the emerging ecosystem of alternatives to NTP. We categorise these approaches into five main families: (1) Multi-Token Prediction, which targets a block of future tokens instead of a single one; (2) Plan-then-Generate, where a global, high-level plan is created upfront to guide token-level decoding; (3) Latent Reasoning, which shifts the autoregressive process itself into a continuous latent space; (4) Continuous Generation Approaches, which replace sequential generation with iterative, parallel refinement through diffusion, flow matching, or energy-based methods; and (5) Non-Transformer Architectures, which sidestep NTP through their inherent model structure. By synthesizing insights across these methods, this survey offers a taxonomy to guide research into models that address the known limitations of token-level generation to develop new transformative models for natural language processing.

We introduce a psychologically grounded and artist-informed framework for modeling visual creativity across four domains: Inner, Outer, Imaginative, and Moral Worlds. Drawing on interviews with practicing artists and theories from psychology, we define 12 traits that capture affective, symbolic, cultural, and ethical dimensions of creativity.Using 20k artworks from the SemArt dataset, we annotate images with GPT 4.1 using detailed, theory-aligned prompts, and evaluate the learnability of these traits from CLIP image embeddings. Traits such as Environmental Dialogicity and Redemptive Arc are predicted with high reliability ($R^2 \approx 0.64 - 0.68$), while others like Memory Imprint remain challenging, highlighting the limits of purely visual encoding. Beyond technical metrics, we visualize a "creativity trait-space" and illustrate how it can support interpretable, trait-aware co-creation - e.g., sliding along a Redemptive Arc axis to explore works of adversity and renewal. By linking cultural-aesthetic insights with computational modeling, our work aims not to reduce creativity to numbers, but to offer shared language and interpretable tools for artists, researchers, and AI systems to collaborate meaningfully.

The platform appears to closely resemble TikTok and is powered by Sora 2, OpenAI's latest video generation model. OpenAI is preparing to launch a stand-alone app for its video generation AI model Sora 2, WIRED has learned. The app, which features a vertical video feed with swipe-to-scroll navigation, appears to closely resemble TikTok--except all of the content is AI-generated . There's a For You-style page powered by a recommendation algorithm. On the right side of the feed, a menu bar gives users the option to like, comment, or remix a video.