Complex reasoning over tabular data is crucial in real-world data analysis, yet large language models (LLMs) often underperform due to complex queries, noisy data, and limited numerical capabilities. To address these issues, we propose TabDSR, a framework consisting of: (1) a query decomposer that breaks down complex questions, (2) a table sanitizer that cleans and filters noisy tables, and (3) a program-of-thoughts (PoT)-based reasoner that generates executable code to derive the final answer from the sanitized table. To ensure unbiased evaluation and mitigate data leakage, we introduce a new dataset, CalTab151, specifically designed for complex numerical reasoning over tables. Experimental results demonstrate that TabDSR consistently outperforms existing methods, achieving state-of-the-art (SOTA) performance with 8.79%, 6.08%, and 19.87% accuracy improvement on TAT-QA, TableBench, and TabDSR, respectively. Moreover, our framework integrates seamlessly with mainstream LLMs, providing a robust solution for complex tabular numerical reasoning. These findings highlight the effectiveness of our framework in enhancing LLM performance for complex tabular numerical reasoning. Data and code are available upon request.

Learning and computation of equilibria are central problems in game theory, theory of computation, and artificial intelligence. In this work, we introduce proximal regret, a new notion of regret based on proximal operators that lies strictly between external and swap regret. When every player employs a no-proximal-regret algorithm in a general convex game, the empirical distribution of play converges to proximal correlated equilibria (PCE), a refinement of coarse correlated equilibria. Our framework unifies several emerging notions in online learning and game theory-such as gradient equilibrium and semicoarse correlated equilibrium-and introduces new ones. Our main result shows that the classic Online Gradient Descent (GD) algorithm achieves an optimal $O(\sqrt{T})$ bound on proximal regret, revealing that GD, without modification, minimizes a stronger regret notion than external regret. This provides a new explanation for the empirically superior performance of gradient descent in online learning and games. We further extend our analysis to Mirror Descent in the Bregman setting and to Optimistic Gradient Descent, which yields faster convergence in smooth convex games.

The integration of AI for Requirements Engineering (RE) presents significant benefits but also poses real challenges. Although RE is fundamental to software engineering, limited research has examined AI adoption in RE. We surveyed 55 software practitioners to map AI usage across four RE phases: Elicitation, Analysis, Specification, and Validation, and four approaches for decision making: human-only decisions, AI validation, Human AI Collaboration (HAIC), and full AI automation. Participants also shared their perceptions, challenges, and opportunities when applying AI for RE tasks. Our data show that 58.2% of respondents already use AI in RE, and 69.1% view its impact as positive or very positive. HAIC dominates practice, accounting for 54.4% of all RE techniques, while full AI automation remains minimal at 5.4%. Passive AI validation (4.4 to 6.2%) lags even further behind, indicating that practitioners value AI's active support over passive oversight. These findings suggest that AI is most effective when positioned as a collaborative partner rather than a replacement for human expertise. It also highlights the need for RE-specific HAIC frameworks along with robust and responsible AI governance as AI adoption in RE grows.

We present an ongoing initiative to provide open, very large, high-quality, and richly annotated textual datasets for almost 200 languages. At 30 trillion tokens, this is likely the largest generally available multilingual collection of LLM pre-training data. These datasets are derived from web crawls from different sources and accompanied with a complete, open-source pipeline for document selection from web archives, text extraction from HTML, language identification for noisy texts, exact and near-deduplication, annotation with, among others, register labels, text quality estimates, and personally identifiable information; and final selection and filtering. We report on data quality probes through contrastive and analytical statistics, through manual inspection of samples for 24 languages, and through end-to-end evaluation of various language model architectures trained on this data. For multilingual LLM evaluation, we provide a comprehensive collection of benchmarks for nine European languages, with special emphasis on natively created tasks, mechanisms to mitigate prompt sensitivity, and refined normalization and aggregation of scores. Additionally, we train and evaluate a family of 57 monolingual encoder-decoder models, as well as a handful of monolingual GPT-like reference models. Besides the monolingual data and models, we also present a very large collection of parallel texts automatically mined from this data, together with a novel parallel corpus synthesized via machine translation.

Automated program repair (APR) has recently shifted toward large language models and agent-based systems, yet most systems rely on local snapshot context, overlooking repository history. Prior work shows that repository history helps repair single-line bugs, since the last commit touching the buggy line is often the bug-introducing one. In this paper, we investigate whether repository history can also improve agentic APR systems at scale, especially for complex multi-hunk bugs. We present HAFixAgent, a History-Aware Bug-Fixing Agent that injects blame-derived repository heuristics into its repair loop. A preliminary study of all 854 real-world bugs from Defects4J motivates our design, showing that bug-relevant history is both widely available and highly concentrated. Empirical comparison of HAFixAgent with two state-of-the-art baselines shows: (1) Effectiveness: HAFixAgent significantly improves over the agent-based baseline (by 212.3%) and the multi-hunk baseline (by 29.9%). (2) Efficiency: history does not significantly increase agent steps and keeps token costs comparable, with notably lower median costs for complex multi-file-multi-hunk bugs. (3) Practicality: combining different historical heuristics repairs more bugs, offering a clear cost-benefit trade-off. HAFixAgent offers a practical recipe for history-aware agentic APR: ground the agent in version control history, prioritize diff-based historical context, and integrate complementary heuristics when needed.

Social media has exacerbated the promotion of Western beauty norms, leading to negative self-image, particularly in women and girls, and causing harm such as body dysmorphia. Increasingly content on the internet has been artificially generated, leading to concerns that these norms are being exaggerated. The aim of this work is to study how generative AI models may encode 'beauty' and erase 'ugliness', and discuss the implications of this for society. To investigate these aims, we create two image generation pipelines: a text-to-image model and a text-to-language model-to image model. We develop a structured beauty taxonomy which we use to prompt three language models (LMs) and two text-to-image models to cumulatively generate 5984 images using our two pipelines. We then recruit women and non-binary social media users to evaluate 1200 of the images through a Likert-scale within-subjects study. Participants show high agreement in their ratings. Our results show that 86.5% of generated images depicted people with lighter skin tones, 22% contained explicit content despite Safe for Work (SFW) training, and 74% were rated as being in a younger age demographic. In particular, the images of non-binary individuals were rated as both younger and more hypersexualised, indicating troubling intersectional effects. Notably, prompts encoded with 'negative' or 'ugly' beauty traits (such as "a wide nose") consistently produced higher Not SFW (NSFW) ratings regardless of gender. This work sheds light on the pervasive demographic biases related to beauty standards present in generative AI models -- biases that are actively perpetuated by model developers, such as via negative prompting. We conclude by discussing the implications of this on society, which include pollution of the data streams and active erasure of features that do not fall inside the stereotype of what is considered beautiful by developers.

Improvisation--the art of spontaneous creation that unfolds moment-to-moment without a scripted outcome--requires practitioners to continuously sense, adapt, and create anew. It is a fundamental mode of human creativity spanning music, dance, and everyday life. The open-ended nature of improvisation produces a stream of novel, unrepeatable moments--an aspect highly valued in artistic creativity. In parallel, open-endedness (OE)--a system's capacity for unbounded novelty and endless "interestingness"--is exemplified in natural or cultural evolution and has been considered "the last grand challenge" in artificial life (ALife). The rise of generative AI now raises the question in computational creativity (CC) research: What makes a "good" improvisation for AI? Can AI learn to improvise in a genuinely open-ended way? In this work-in-progress paper, we report insights from in-depth interviews with 6 experts in improvisation across dance, music, and contact improvisation. We draw systemic connections between human improvisa-tional arts and the design of future experiential AI agents that could improvise alone or alongside humans--or even with other AI agents--embodying qualities of improvisation drawn from practice: active listening (umwelt and awareness), being in the time (mindfulness and ephemerality), embracing the unknown (source of randomness and serendipity), non-judgmental flow (acceptance and dynamical stability, balancing structure and surprise (unpredictable criticality at edge of chaos), imaginative metaphor (synaesthesia and planning), empathy, trust, boundary, and care (mutual theory of mind), and playfulness and intrinsic motivation (maintaining interestingness).

Microsoft Copilot suites serve as the universal entry point for various agents skilled in handling important tasks, ranging from assisting a customer with product purchases to detecting vulnerabilities in corporate programming code. Each agent can be powered by language models, software engineering operations, such as database retrieval, and internal \& external knowledge. The repertoire of a copilot can expand dynamically with new agents. This requires a robust orchestrator that can distribute tasks from user prompts to the right agents. In this work, we propose an Agentic Meta-orchestrator (AMO) for handling multiple tasks and scalable agents in copilot services, which can provide both natural language and action responses. We will also demonstrate the planning that leverages meta-learning, i.e., a trained decision tree model for deciding the best inference strategy among various agents/models. We showcase the effectiveness of our AMO through two production use cases: Microsoft 365 (M365) E-Commerce Copilot and code compliance copilot. M365 E-Commerce Copilot advertises Microsoft products to external customers to promote sales success. The M365 E-Commerce Copilot provides up-to-date product information and connects to multiple agents, such as relational databases and human customer support. The code compliance copilot scans the internal DevOps code to detect known and new compliance issues in pull requests (PR).

Humanoid robots represent a central frontier in embodied intelligence, as their anthropomorphic form enables natural deployment in humans' workspace. Brain-body co-design for humanoids presents a promising approach to realizing this potential by jointly optimizing control policies and physical morphology. Within this context, fall recovery emerges as a critical capability. It not only enhances safety and resilience but also integrates naturally with locomotion systems, thereby advancing the autonomy of humanoids. In this paper, we propose RoboCraft, a scalable humanoid co-design framework for fall recovery that iteratively improves performance through the coupled updates of control policy and morphology. A shared policy pretrained across multiple designs is progressively finetuned on high-performing morphologies, enabling efficient adaptation without retraining from scratch. Concurrently, morphology search is guided by human-inspired priors and optimization algorithms, supported by a priority buffer that balances reevaluation of promising candidates with the exploration of novel designs. Experiments show that RoboCraft achieves an average performance gain of 44.55% on seven public humanoid robots, with morphology optimization drives at least 40% of improvements in co-designing four humanoid robots, underscoring the critical role of humanoid co-design.

Advanced AI systems sometimes act in ways that differ from human intent. To gather clear, reproducible examples, we ran the Misalignment Bounty: a crowdsourced project that collected cases of agents pursuing unintended or unsafe goals. The bounty received 295 submissions, of which nine were awarded. This report explains the program's motivation and evaluation criteria, and walks through the nine winning submissions step by step.