Large language models (LLMs) have demonstrated impressive reasoning capabilities when provided with chain-of-thought exemplars, but curating large reasoning datasets remains laborious and resource-intensive. In this work, we introduce Prompting Test-Time Scaling (P-TTS), a simple yet effective inference-time data augmentation strategy for enhancing LLM reasoning through finetuning. Rather than collecting thousands or even millions of examples, P-TTS leverages a small pool of only 90 manually selected reasoning instances and systematically varies exemplar augmentation through principled instruction prompting intensities at test time to synthesize diverse reasoning trajectory contexts. Then we finetune the various sizes of Qwen-2.5 models on P-TTS data. Across a suite of mathematical reasoning AIME2024 & 25, MATH500, and GPQA-Diamond, our P-TTS-7B and 32B models outperform the prior competitive baselines like S1 and S1.1 (1K-shot), achieving absolute accuracy gains of +26.66% and +30.00% on AIME'24 (7B), and +13.34% and +6.67% on AIME'25 (7B); P-TTS-32B yields gains of +23.33% and +16.63% on AIME'24, and +26.63% and +3.33% on AIME'25 (vs. S1 and S1.1, respectively), with comparable or better performance on MATH500 and GPQA-Diamond. We further show that P-TTS enhances zero-shot generalization accuracy on out-of-domain reasoning benchmarks of Gaokao, Kaoyan, OlympiadBench, AMC23, GradeSchoolMath, and Minerva. Our analysis suggests that test-time scaling effectively explores the latent space of reasoning patterns, amplifying LLM problem-solving with minimal annotation overhead, and further unlocking the reasoning potential and capabilities of LLMs. Prompting Test-Time Scaling offers a practical, low-cost way to elicit LLM reasoning in resource-constrained or rapidly evolving domains.

Today's generative models thrive with large amounts of supervised data and informative reward functions characterizing the quality of the generation. They work under the assumptions that the supervised data provides knowledge to pre-train the model, and the reward function provides dense information about how to further improve the generation quality and correctness. However, in the hardest instances of important problems, two problems arise: (1) the base generative model attains a near-zero reward signal, and (2) calls to the reward oracle are expensive. This setting poses a fundamentally different learning challenge than standard reward-based post-training. To address this, we propose BaNEL (Bayesian Negative Evidence Learning), an algorithm that post-trains the model using failed attempts only, while minimizing the number of reward evaluations (NREs). Our method is based on the idea that the problem of learning regularities underlying failures can be cast as another, in-loop generative modeling problem. We then leverage this model to assess whether new data resembles previously seen failures and steer the generation away from them. We show that BaNEL can improve model performance without observing a single successful sample on several sparse-reward tasks, outperforming existing novelty-bonus approaches by up to several orders of magnitude in success rate, while using fewer reward evaluations.

Time series data often contain latent temporal structure, transitions between locally stationary regimes, repeated motifs, and bursts of variability, that are rarely leveraged in standard representation learning pipelines. Existing models typically operate on raw or fixed-window sequences, treating all time steps as equally informative, which leads to inefficiencies, poor robustness, and limited scalability in long or noisy sequences. We propose STaTS, a lightweight, unsupervised framework for Structure-Aware Temporal Summarization that adaptively compresses both univariate and multivariate time series into compact, information-preserving token sequences. STaTS detects change points across multiple temporal resolutions using a BIC-based statistical divergence criterion, then summarizes each segment using simple functions like the mean or generative models such as GMMs. This process achieves up to 30x sequence compression while retaining core temporal dynamics. STaTS operates as a model-agnostic preprocessor and can be integrated with existing unsupervised time series encoders without retraining. Extensive experiments on 150+ datasets, including classification tasks on the UCR-85, UCR-128, and UEA-30 archives, and forecasting on ETTh1 and ETTh2, ETTm1, and Electricity, demonstrate that STaTS enables 85-90\% of the full-model performance while offering dramatic reductions in computational cost. Moreover, STaTS improves robustness under noise and preserves discriminative structure, outperforming uniform and clustering-based compression baselines. These results position STaTS as a principled, general-purpose solution for efficient, structure-aware time series modeling.

Researchers have pursued neurosymbolic artificial intelligence (AI) applications for nearly three decades because symbolic components provide abstraction while neural components provide generalization. Thus, a marriage of the two components can lead to rapid advancements in AI. Yet, the field has not realized this promise since most neurosymbolic AI frameworks fail to scale. In addition, the implicit representations and approximate reasoning of neural approaches limit interpretability and trust. Knowledge graphs (KGs), a gold-standard representation of explicit semantic knowledge, can address the symbolic side. However, automatically deriving reliable KGs from text corpora has remained an open problem. We address these challenges by introducing GraphMERT, a tiny graphical encoder-only model that distills high-quality KGs from unstructured text corpora and its own internal representations. GraphMERT and its equivalent KG form a modular neurosymbolic stack: neural learning of abstractions; symbolic KGs for verifiable reasoning. GraphMERT + KG is the first efficient and scalable neurosymbolic model to achieve state-of-the-art benchmark accuracy along with superior symbolic representations relative to baselines. Concretely, we target reliable domain-specific KGs that are both (1) factual (with provenance) and (2) valid (ontology-consistent relations with domain-appropriate semantics). When a large language model (LLM), e.g., Qwen3-32B, generates domain-specific KGs, it falls short on reliability due to prompt sensitivity, shallow domain expertise, and hallucinated relations. On text obtained from PubMed papers on diabetes, our 80M-parameter GraphMERT yields a KG with a 69.8% FActScore; a 32B-parameter baseline LLM yields a KG that achieves only 40.2% FActScore. The GraphMERT KG also attains a higher ValidityScore of 68.8%, versus 43.0% for the LLM baseline.

Reasoning models have recently shown remarkable progress in domains such as math and coding. However, their expert-level abilities in math and coding contrast sharply with their performance in long-horizon, interactive tasks such as web navigation and computer/phone-use. Inspired by literature on human cognition, we argue that current AI agents need ''vicarious trial and error'' - the capacity to mentally simulate alternative futures before acting - in order to enhance their understanding and performance in complex interactive environments. We introduce Dyna-Mind, a two-stage training framework that explicitly teaches (V)LM agents to integrate such simulation into their reasoning. In stage 1, we introduce Reasoning with Simulations (ReSim), which trains the agent to generate structured reasoning traces from expanded search trees built from real experience gathered through environment interactions. ReSim thus grounds the agent's reasoning in faithful world dynamics and equips it with the ability to anticipate future states in its reasoning. In stage 2, we propose Dyna-GRPO, an online reinforcement learning method to further strengthen the agent's simulation and decision-making ability by using both outcome rewards and intermediate states as feedback from real rollouts. Experiments on two synthetic benchmarks (Sokoban and ALFWorld) and one realistic benchmark (AndroidWorld) demonstrate that (1) ReSim effectively infuses simulation ability into AI agents, and (2) Dyna-GRPO leverages outcome and interaction-level signals to learn better policies for long-horizon, planning-intensive tasks. Together, these results highlight the central role of simulation in enabling AI agents to reason, plan, and act more effectively in the ever more challenging environments.

There are many critical challenges in optimizing neural network models, including distributed computing, compression techniques, and efficient training, regardless of their application to specific tasks. Solving such problems is crucial because the need for scalable and resource-efficient models is increasing. To address these challenges, we have developed a new automated machine learning (AutoML) framework, Parameter Efficient Training with Robust Automation (PETRA). It applies evolutionary optimization to model architecture and training strategy. PETRA includes pruning, quantization, and loss regularization. Experimental studies on real-world data with financial event sequences, as well as image and time-series -- benchmarks, demonstrate PETRA's ability to improve neural model performance and scalability -- namely, a significant decrease in model size (up to 75%) and latency (up to 33%), and an increase in throughput (by 13%) without noticeable degradation in the target metric.

Large reasoning models (LRMs) increasingly rely on step-by-step Chain-of-Thought (CoT) reasoning to improve task performance, particularly in high-resource languages such as English. While recent work has examined final-answer accuracy in multilingual settings, the thinking traces themselves, i.e., the intermediate steps that lead to the final answer, remain underexplored. In this paper, we present the first comprehensive study of multilingual CoT reasoning, evaluating three key dimensions: performance, consistency, and faithfulness. We begin by measuring language compliance, answer accuracy, and answer consistency when LRMs are explicitly instructed or prompt-hacked to think in a target language, revealing strong language preferences and divergent performance across languages. Next, we assess crosslingual consistency of thinking traces by interchanging them between languages. We find that the quality and effectiveness of thinking traces vary substantially depending on the prompt language. Finally, we adapt perturbation-based techniques -- i.e., truncation and error injection -- to probe the faithfulness of thinking traces across languages, showing that models rely on traces to varying degrees. We release our code and data to support future research.

By the end of 2024, Google researchers introduced Titans: Learning at Test Time, a neural memory model achieving strong empirical results across multiple tasks. However, the lack of publicly available code and ambiguities in the original description hinder reproducibility. In this work, we present a lightweight reimplementation of Titans and conduct a comprehensive evaluation on Masked Language Modeling, Time Series Forecasting, and Recommendation tasks. Our results reveal that Titans does not always outperform established baselines due to chunking. However, its Neural Memory component consistently improves performance compared to attention-only models. These findings confirm the model's innovative potential while highlighting its practical limitations and raising questions for future research.

Pre-trained transformer-based models have significantly advanced automatic speech recognition (ASR), yet they remain sensitive to accent and dialectal variations, resulting in elevated word error rates (WER) in linguistically diverse languages such as English and Persian. To address this challenge, we propose an accent-invariant ASR framework that integrates accent and dialect classification into the recognition pipeline. Our approach involves training a spectrogram-based classifier to capture accent-specific cues, masking the regions most influential to its predictions, and using the masked spectrograms for data augmentation. This enhances the robustness of ASR models against accent variability. We evaluate the method using both English and Persian speech. For Persian, we introduce a newly collected dataset spanning multiple regional accents, establishing the first systematic benchmark for accent variation in Persian ASR that fills a critical gap in multilingual speech research and provides a foundation for future studies on low-resource, linguistically diverse languages. Experimental results with the Whisper model demonstrate that our masking and augmentation strategy yields substantial WER reductions in both English and Persian settings, confirming the effectiveness of the approach. This research advances the development of multilingual ASR systems that are resilient to accent and dialect diversity. Code and dataset are publicly available at: https://github.com/MH-Sameti/Accent_invariant_ASR

Estimating model performance without labels is an important goal for understanding how NLP models generalize. While prior work has proposed measures based on dataset similarity or predicted correctness, it remains unclear when these estimates produce reliable performance rankings across domains. In this paper, we analyze the factors that affect ranking reliability using a two-step evaluation setup with four base classifiers and several large language models as error predictors. Experiments on the GeoOLID and Amazon Reviews datasets, spanning 15 domains, show that large language model-based error predictors produce stronger and more consistent rank correlations with true accuracy than drift-based or zero-shot baselines. Our analysis reveals two key findings: ranking is more reliable when performance differences across domains are larger, and when the error model's predictions align with the base model's true failure patterns. These results clarify when performance estimation methods can be trusted and provide guidance for their use in cross-domain model evaluation.