The proliferation of Large Language Models (LLMs) necessitates valid evaluation methods to guide downstream applications and actionable future improvements. The Item Response Theory (IRT) has recently emerged as a promising framework for evaluating LLMs via their response accuracy. Beyond simple response accuracy, LLMs' chain of thought (CoT) lengths serve as a vital indicator of their reasoning ability. To leverage the CoT length information to assist the evaluation of LLMs, we propose Latency-Response Theory (LaRT) to jointly model the response accuracy and CoT length by introducing the latent ability, latent speed, and a key correlation parameter between them. We derive an efficient estimation algorithm and establish rigorous identifiability results for the population parameters to ensure the statistical validity of estimation. Theoretical asymptotic analyses and simulation studies demonstrate LaRT's advantages over IRT in terms of higher estimation accuracy and shorter confidence intervals for latent traits. A key finding is that the asymptotic estimation precision of the latent ability under LaRT exceeds that of IRT whenever the latent ability and latent speed are correlated. We collect real responses from diverse LLMs on popular benchmark datasets. The application of LaRT reveals a strong negative correlation between the latent ability and latent speed in all benchmarks, with stronger correlation for more difficult benchmarks. This finding supports the intuition that higher reasoning ability correlates with slower speed and longer response latency. LaRT yields different LLM rankings than IRT and outperforms IRT across multiple key evaluation metrics including predictive power, item efficiency, ranking validity, and LLM evaluation efficiency. Code and data are available at https://github.com/Toby-X/Latency-Response-Theory-Model.

This paper presents HunyuanOCR, a commercial-grade, open-source, and lightweight (1B parameters) Vision-Language Model (VLM) dedicated to OCR tasks. The architecture comprises a Native Vision Transformer (ViT) and a lightweight LLM connected via an MLP adapter. HunyuanOCR demonstrates superior performance, outperforming commercial APIs, traditional pipelines, and larger models (e.g., Qwen3-VL-4B). Specifically, it surpasses current public solutions in perception tasks (Text Spotting, Parsing) and excels in semantic tasks (IE, Text Image Translation), securing first place in the ICDAR 2025 DIMT Challenge (Small Model Track). Furthermore, it achieves state-of-the-art (SOTA) results on OCRBench among VLMs with fewer than 3B parameters. HunyuanOCR achieves breakthroughs in three key aspects: 1) Unifying Versatility and Efficiency: We implement comprehensive support for core capabilities including spotting, parsing, IE, VQA, and translation within a lightweight framework. This addresses the limitations of narrow "OCR expert models" and inefficient "General VLMs". 2) Streamlined End-to-End Architecture: Adopting a pure end-to-end paradigm eliminates dependencies on pre-processing modules (e.g., layout analysis). This fundamentally resolves error propagation common in traditional pipelines and simplifies system deployment. 3) Data-Driven and RL Strategies: We confirm the critical role of high-quality data and, for the first time in the industry, demonstrate that Reinforcement Learning (RL) strategies yield significant performance gains in OCR tasks. HunyuanOCR is officially open-sourced on HuggingFace. We also provide a high-performance deployment solution based on vLLM, placing its production efficiency in the top tier. We hope this model will advance frontier research and provide a solid foundation for industrial applications.

We revisit continual pre-training for large language models and argue that progress now depends more on scaling the right structure than on scaling parameters alone. We introduce SCALE, a width upscaling architecture that inserts lightweight expansion into linear modules while freezing all pre-trained parameters. This preserves the residual and attention topologies and increases capacity without perturbing the base model's original functionality. SCALE is guided by two principles: Persistent Preservation, which maintains the base model's behavior via preservation-oriented initialization and freezing of the pre-trained weights, and Collaborative Adaptation, which selectively trains a subset of expansion components to acquire new knowledge with minimal interference. We instantiate these ideas as SCALE-Preserve (preservation-first), SCALE-Adapt (adaptation-first), and SCALE-Route, an optional routing extension that performs token-level routing between preservation and adaptation heads. On a controlled synthetic biography benchmark, SCALE mitigates the severe forgetting observed with depth expansion while still acquiring new knowledge. In continual pre-training on a Korean corpus, SCALE variants achieve less forgetting on English evaluations and competitive gains on Korean benchmarks, with these variants offering the best overall stability-plasticity trade-off. Accompanying analysis clarifies when preservation provably holds and why the interplay between preservation and adaptation stabilizes optimization compared to standard continual learning setups.

Optimization modeling enables critical decisions across industries but remains difficult to automate: informal language must be mapped to precise mathematical formulations and executable solver code. Prior LLM approaches either rely on brittle prompting or costly retraining with limited generalization. We present AlphaOPT, a self-improving experience library that enables an LLM to learn from limited demonstrations (even answers alone, without gold-standard programs) and solver feedback - without annotated reasoning traces or parameter updates. AlphaOPT operates in a continual two-phase cycle: (i) a Library Learning phase that reflects on failed attempts, extracting solver-verified, structured insights as {taxonomy, condition, explanation, example}; and (ii) a Library Evolution phase that diagnoses retrieval misalignments and refines the applicability conditions of stored insights, improving transfer across tasks. This design (1) learns efficiently from limited demonstrations without curated rationales, (2) expands continually without costly retraining by updating the library rather than model weights, and (3) makes knowledge explicit and interpretable for human inspection and intervention. Experiments show that AlphaOPT steadily improves with more data (65% to 72% from 100 to 300 training items) and surpasses the strongest baseline by 7.7% on the out-of-distribution OptiBench dataset when trained only on answers. Code and data are available at: https://github.com/Minw913/AlphaOPT.

ORCID: 0000 -0003-2811-1194 Abstract --As design thinking education is growing in secondary and tertiary education, educators face a mounting challenge of evaluating creative artefacts that comprise visual and textual elements. Traditional, rubric-based methods of assessment are laborious, time-consuming, and inconsistent, due to their reliance on Teaching Assistants (TAs) in large, multi - section cohorts. This paper presents an exploratory study to investigate the reliability and perceived accuracy of AI -assisted assessment vis -à -vis TA-assisted assessment in evaluating student posters in design thinking education. Two activities were conducted with 33 Ministry of Education (MOE), Singapore school teachers, with the objective (1) to compare AI -generated scores with TA grading across three key dimensions: empathy and user understanding, identification of pain points and opportunities, and visual communication, and (2) to understand teacher preferences for AI-assigned, TA-assigned, and hybrid scores. Results showed low statistical agreement between instructor and AI scores for empathy and pain points, though slightly higher alignment for visual communication. Teachers generally preferred TA -assigned scores in six of ten samples. Qualitative feedback highlighted AI's potential for formative feedback, consistency, and student self -reflection, but raised concerns about its limitations in capturing contextual nuance and creative insight. The study underscores the need for hybrid assessment models that integrate computational efficiency with human insights . This research contributes to the evolving conversation around responsible AI adoption in creative disciplines, emphasizing the balance between automation and human judgment for scalable and pedagogically sound assessment practices. Design thinking is a human-centered approach to innovation that draws from the designer's toolkit to integrate the needs of people, the possibilities of technology, and the requirements for business success. It is a non - linear, iterative process that teams use to understand users, challenge assumptions, redefine problems, and create innovative solutions to prototype and test.

The rise of Artificial Intelligence (AI) is reshaping how software systems are developed and maintained. However, AI-based systems give rise to new software issues that existing detection tools often miss. Among these, we focus on AI-specific code smells, recurring patterns in the code that may indicate deeper problems such as unreproducibility, silent failures, or poor model generalization. We introduce SpecDetect4AI, a tool-based approach for the specification and detection of these code smells at scale. This approach combines a high-level declarative Domain-Specific Language (DSL) for rule specification with an extensible static analysis tool that interprets and detects these rules for AI-based systems. We specified 22 AI-specific code smells and evaluated SpecDetect4AI on 826 AI-based systems (20M lines of code), achieving a precision of 88.66% and a recall of 88.89%, outperforming other existing detection tools. Our results show that SpecDetect4AI supports the specification and detection of AI-specific code smells through dedicated rules and can effectively analyze large AI-based systems, demonstrating both efficiency and extensibility (SUS 81.7/100).

Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization methods offer preliminary solutions, they fall short in cold-start scenarios and long-term personalization due to their inherently static and shallow designs. In this work, we introduce the Reinforcement Learning for Personalized Alignment (RLPA) framework, in which an LLM interacts with a simulated user model to iteratively infer and refine user profiles through dialogue. The training process is guided by a dual-level reward structure: the Profile Reward encourages accurate construction of user representations, while the Response Reward incentivizes generation of responses consistent with the inferred profile. We instantiate RLPA by fine-tuning Qwen-2.5-3B-Instruct, resulting in Qwen-RLPA, which achieves state-of-the-art performance in personalized dialogue. Empirical evaluations demonstrate that Qwen-RLPA consistently outperforms prompting and offline fine-tuning baselines, and even surpasses advanced commercial models such as Claude-3.5 and GPT-4o. Further analysis highlights Qwen-RLPA's robustness in reconciling conflicting user preferences, sustaining long-term personalization and delivering more efficient inference compared to recent reasoning-focused LLMs. These results emphasize the potential of dynamic profile inference as a more effective paradigm for building personalized dialogue systems.

Online class-incremental learning (OCIL) focuses on gradually learning new classes (called plasticity) from a stream of data in a single-pass, while concurrently preserving knowledge of previously learned classes (called stability). The primary challenge in OCIL lies in maintaining a good balance between the knowledge of old and new classes within the continually updated model. Most existing methods rely on explicit knowledge interaction through experience replay, and often employ exclusive training separation to address bias problems. Nevertheless, it still remains a big challenge to achieve a well-balanced learner, as these methods often exhibit either reduced plasticity or limited stability due to difficulties in continually integrating knowledge in the OCIL setting. In this paper, we propose a novel replay-based method, called Balanced Inclusive Separation for Online iNcremental learning (BISON), which can achieve both high plasticity and stability, thus ensuring more balanced performance in OCIL. Our BISON method proposes an inclusive training separation strategy using dual classifiers so that knowledge from both old and new classes can effectively be integrated into the model, while introducing implicit approaches for transferring knowledge across the two classifiers. Extensive experimental evaluations over three widely-used OCIL benchmark datasets demonstrate the superiority of BISON, showing more balanced yet better performance compared to state-of-the-art replay-based OCIL methods.

Composite federated learning offers a general framework for solving machine learning problems with additional regularization terms. However, existing methods often face significant limitations: many require clients to perform computationally expensive proximal operations, and their performance is frequently vulnerable to data heterogeneity. To overcome these challenges, we propose a novel composite federated learning algorithm called \textbf{FedCanon}, designed to solve the optimization problems comprising a possibly non-convex loss function and a weakly convex, potentially non-smooth regularization term. By decoupling proximal mappings from local updates, FedCanon requires only a single proximal evaluation on the server per iteration, thereby reducing the overall proximal computation cost. Concurrently, it integrates control variables into local updates to mitigate the client drift arising from data heterogeneity. The entire architecture avoids the complex subproblems of primal-dual alternatives. The theoretical analysis provides the first rigorous convergence guarantees for this proximal-skipping framework in the general non-convex setting. It establishes that FedCanon achieves a sublinear convergence rate, and a linear rate under the Polyak-Łojasiewicz condition, without the restrictive bounded heterogeneity assumption. Extensive experiments demonstrate that FedCanon outperforms the state-of-the-art methods in terms of both accuracy and computational efficiency, particularly under heterogeneous data distributions.

Retrieval-augmented generation (RAG) with large language models (LLMs) has demonstrated strong performance in multilingual question-answering (QA) tasks by leveraging relevant passages retrieved from corpora. In multilingual RAG (mRAG), the retrieved passages can be written in languages other than that of the query entered by the user, making it challenging for LLMs to effectively utilize the provided information. Recent research suggests that retrieving passages from multilingual corpora can improve RAG performance, particularly for low-resource languages. However, the extent to which LLMs can leverage different kinds of multilingual contexts to generate accurate answers, *independently from retrieval quality*, remains understudied. In this paper, we conduct an extensive assessment of LLMs' ability to (i) make consistent use of a relevant passage regardless of its language, (ii) respond in the expected language, and (iii) focus on the relevant passage even when multiple `distracting' passages in different languages are provided in the context. Our experiments with four LLMs across three QA datasets covering a total of 48 languages reveal a surprising ability of LLMs to extract the relevant information from passages in a different language than the query, but a much weaker ability to formulate a full answer in the correct language. Our analysis, based on both accuracy and feature attribution techniques, further shows that distracting passages negatively impact answer quality regardless of their language. However, distractors in the query language exert a slightly stronger influence. Taken together, our findings deepen the understanding of how LLMs utilize context in mRAG systems, providing directions for future improvements.