Modern enterprises generate vast streams of time series metrics when monitoring complex systems, known as observability data. Unlike conventional time series from domains such as weather, observability data are zero-inflated, highly stochastic, and exhibit minimal temporal structure. Despite their importance, observability datasets are underrepresented in public benchmarks due to proprietary restrictions. Existing datasets are often anonymized and normalized, removing scale information and limiting their use for tasks beyond forecasting, such as anomaly detection, root-cause analysis, and multi-modal reasoning. To address this gap, we introduce TelecomTS, a large-scale observability dataset derived from a 5G telecommunications network. TelecomTS features heterogeneous, de-anonymized covariates with explicit scale information and supports a suite of downstream tasks, including anomaly detection, root-cause analysis, and a question-answering benchmark requiring multi-modal reasoning. Benchmarking state-of-the-art time series, language, and reasoning models reveals that existing approaches struggle with the abrupt, noisy, and high-variance dynamics of observability data. Our experiments also underscore the importance of preserving covariates' absolute scale, emphasizing the need for foundation time series models that natively leverage scale information for practical observability applications.

Recent Large Language Model (LLM) post-training methods rely on token-level clipping mechanisms during Reinforcement Learning (RL). However, we identify a fundamental flaw in this Outcome-Supervised RL (OSRL) paradigm: the Importance Sampling (IS) ratios of positive-advantage tokens are mismatched, leading to unbalanced token weighting for positive and negative tokens. This mismatch suppresses the update of low-probability tokens while over-amplifying already high-probability ones. To address this, we propose Asymmetric Importance Sampling Policy Optimization (ASPO), which uses a simple yet effective strategy that flips the IS ratios of positive-advantage tokens, aligning their update direction with the learning dynamics of negative ones. AIS further incorporates a soft dual-clipping mechanism to stabilize extreme updates while maintaining gradient flow. Comprehensive experiments on coding and mathematical reasoning benchmarks demonstrate that ASPO significantly mitigates premature convergence, improves training stability, and enhances final performance over strong GRPO-based baselines. Our analysis provides new insights into the role of token-level weighting in OSRL and highlights the critical importance of correcting IS in LLM RL. The code and models of ASPO are available at https://github.com/wizard-III/Archer2.0.

Large language models hold promise as scientific assistants, yet existing agents either rely solely on algorithm evolution or on deep research in isolation, both of which face critical limitations. Pure algorithm evolution, as in AlphaEvolve, depends only on the internal knowledge of LLMs and quickly plateaus in complex domains, while pure deep research proposes ideas without validation, resulting in unrealistic or unimplementable solutions. We present DeepEvolve, an agent that integrates deep research with algorithm evolution, uniting external knowledge retrieval, cross-file code editing, and systematic debugging under a feedback-driven iterative loop. Each iteration not only proposes new hypotheses but also refines, implements, and tests them, avoiding both shallow improvements and unproductive over-refinements. Across nine benchmarks in chemistry, mathematics, biology, materials, and patents, DeepEvolve consistently improves the initial algorithm, producing executable new algorithms with sustained gains. By bridging the gap between unguided evolution and research without grounding, DeepEvolve provides a reliable framework for advancing scientific algorithm discovery. Our code is available at https://github.com/liugangcode/deepevolve.

Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step introduces substantial redundancy, as sub-problems vary widely in difficulty and complexity: a small number of pivotal steps are genuinely challenging and decisive for the final answer, while many others only involve straightforward revisions or simple computations. Therefore, a natural idea is to endow reasoning models with the ability to adaptively respond to this variation, rather than treating all steps with the same level of elaboration. To this end, we propose MixReasoning, a framework that dynamically adjusts the depth of reasoning within a single response. The resulting chain of thought then becomes a mixture of detailed reasoning on difficult steps and concise inference on simpler ones. Experiments on GSM8K, MA TH-500, and AIME show that MixReasoning shortens reasoning length and substantially improves efficiency without compromising accuracy. Large Reasoning Models (LRMs) such as DeepSeek-R1 (Guo et al., 2025) and Qwen3 (Y ang et al., 2025a) have achieved state-of-the-art results on a wide range of complex tasks, spanning arithmetic, commonsense, and scientific reasoning. A key driver of these gains is the use of long chains of thought (CoTs) (Wei et al., 2022) that externalize intermediate computations before arriving at a final answer (Jaech et al., 2024).

Understanding hour-long videos with multi-modal large language models (MM-LLMs) enriches the landscape of human-centered AI applications. However, for end-to-end video understanding with LLMs, uniformly sampling video frames results in LLMs being overwhelmed by a vast amount of irrelevant information as video length increases. Existing hierarchical key frame extraction methods improve the accuracy of video understanding but still face two critical challenges. 1) How can the interference of extensive redundant information in long videos be mitigated? 2) How can a model dynamically adapt to complex hierarchical structures while accurately identifying key frames? To address these issues, we propose VideoMiner, which iteratively segments, captions, and clusters long videos, forming a hierarchical tree structure. The proposed VideoMiner progresses from long videos to events to frames while preserving temporal coherence, effectively addressing the first challenge. To precisely locate key frames, we introduce T-GRPO, a tree-based group relative policy optimization in reinforcement learning method that guides the exploration of the VideoMiner. The proposed T-GRPO is specifically designed for tree structures, integrating spatiotemporal information at the event level while being guided by the question, thus solving the second challenge. We achieve superior performance in all long-video understanding tasks and uncover several interesting insights. Our proposed T-GRPO surprisingly incentivizes the model to spontaneously generate a reasoning chain. Additionally, the designed tree growth auxin dynamically adjusts the expansion depth, obtaining accuracy and efficiency gains. The code is publicly available at https://github.com/caoxinye/VideoMiner.

Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain poorly understood. In this work, we investigate why safety alignment fails in reasoning models through a mechanistic interpretability lens. Using a linear probing approach to trace refusal intentions across token positions, we discover a striking phenomenon termed as refusal cliff: many poorly-aligned reasoning models correctly identify harmful prompts and maintain strong refusal intentions during their thinking process, but experience a sharp drop in refusal scores at the final tokens before output generation. This suggests that these models are not inherently unsafe; rather, their refusal intentions are systematically suppressed. Through causal intervention analysis, we identify a sparse set of attention heads that negatively contribute to refusal behavior. Ablating just 3% of these heads can reduce attack success rates below 10%. Building on these mechanistic insights, we propose Cliff-as-a-Judge, a novel data selection method that identifies training examples exhibiting the largest refusal cliff to efficiently repair reasoning models' safety alignment. This approach achieves comparable safety improvements using only 1.7% of the vanilla safety training data, demonstrating a less-is-more effect in safety alignment. Code is available at here. Large Reasoning Models (Guo et al., 2025; Shao et al., 2024; Hugging Face, 2025), with advanced reasoning capability derived from reinforcement learning with verifiable rewards (RL VR) (Y u et al., 2025; Liu et al., 2025a), are designed to handle complex problem solving, logical inference, and tool-assisted planning.

Recent studies employing Large Language Models (LLMs) to test the Argument from the Poverty of the Stimulus (APS) have yielded contrasting results across syntactic phenomena. This paper investigates the hypothesis that characteristics of the stimuli used in recent studies, including lexical ambiguities and structural complexities, may confound model performance. A methodology is proposed for re-evaluating LLM competence on syntactic prediction, focusing on GPT-2. This involves: 1) establishing a baseline on previously used (both filtered and unfiltered) stimuli, and 2) generating a new, refined dataset using a state-of-the-art (SOTA) generative LLM (Gemini 2.5 Pro Preview) guided by linguistically-informed templates designed to mitigate identified confounds. Our preliminary findings indicate that GPT-2 demonstrates notably improved performance on these refined PG stimuli compared to baselines, suggesting that stimulus quality significantly influences outcomes in surprisal-based evaluations of LLM syntactic competency.

Test-time scaling has emerged as a transformative paradigm for enhancing the performance of large reasoning models, enabling dynamic allocation of computational resources during inference. However, as the landscape of reasoning models rapidly expands, a critical question remains: how can we systematically compare and evaluate the test-time scaling capabilities across different models? In this paper, we introduce ARISE (Adaptive Resolution-aware Scaling Evaluation), a novel metric specifically designed to assess the test-time scaling effectiveness of large reasoning models. Unlike existing evaluation approaches, ARISE incorporates two key innovations: (1) sample-level awareness that effectively penalizes negative scaling behaviors where increased computation leads to performance degradation, and (2) a dynamic sampling mechanism that mitigates the impact of accuracy fluctuations and token count instability on the final assessment. We conduct comprehensive experiments evaluating state-of-the-art reasoning models across diverse domains including mathematical reasoning, code generation, and agentic tasks. Our results demonstrate that ARISE provides a reliable and fine-grained measurement of test-time scaling capabilities, revealing significant variations in scaling efficiency across models. Notably, our evaluation identifies Claude Opus as exhibiting superior scaling characteristics compared to other contemporary reasoning models.

This study examines the use of social media and news images to detect and measure hailstones, utilizing pre-trained multimodal large language models. The dataset for this study comprises 474 crowdsourced images of hailstones from documented hail events in Austria, which occurred between January 2022 and September 2024. These hailstones have maximum diameters ranging from 2 to 11cm. We estimate the hail diameters and compare four different models utilizing one-stage and two-stage prompting strategies. The latter utilizes additional size cues from reference objects, such as human hands, within the image. Our results show that pretrained models already have the potential to measure hailstone diameters from images with an average mean absolute error of 1.12cm for the best model. In comparison to a single-stage prompt, two-stage prompting improves the reliability of most models. Our study suggests that these off-the-shelf models, even without fine-tuning, can complement traditional hail sensors by extracting meaningful and spatially dense information from social media imagery, enabling faster and more detailed assessments of severe weather events. The automated real-time image harvesting from social media and other sources remains an open task, but it will make our approach directly applicable to future hail events.

Low-Rank Adaptation (LoRA) has emerged as a dominant method in Parameter-Efficient Fine-Tuning (PEFT) for large language models, which augments the transformer layer with one down-projection $A$ and one up-projection $B$. However, LoRA's reliance on a single down-projection matrix ($A$) creates a representational bottleneck, as this solitary feature extractor is inherently insufficient for capturing the diverse signals required by complex tasks. This motivates our architectural shift to focus on enriching the feature adaptation to improve the downstream task adaptation ability. We propose MASA (Multi-$A$ Shared Adaptation), an architecture that implements a multi-$A$, single-$B$ structure where the multi-$A$ expert ensemble is asymmetrically shared across layers to ensure parameter efficiency. In MASA, these specialized experts capture diverse features, which are then integrated by a single, layer-specific $B$-matrix. The effectiveness and versatility of our method are validated through a comprehensive suite of experiments spanning multi-domain generalization, single-domain specialization, and multi-task reasoning. For example, on the MMLU benchmark, MASA achieves an average accuracy of 59.62%, outperforming the standard LoRA by 1.08 points (a relative improvement of 1.84%) with comparable learnable parameters of 0.52%.