Reinforcement learning (RL) has proven effective for fine-tuning large language models (LLMs), significantly enhancing their reasoning abilities in domains such as mathematics and code generation. A crucial factor influencing RL fine-tuning success is the training curriculum: the order in which training problems are presented. While random curricula serve as common baselines, they remain suboptimal; manually designed curricula often rely heavily on heuristics, and online filtering methods can be computationally prohibitive. To address these limitations, we propose Self-Evolving Curriculum (SEC), an automatic curriculum learning method that learns a curriculum policy concurrently with the RL fine-tuning process. Our approach formulates curriculum selection as a non-stationary Multi-Armed Bandit problem, treating each problem category (e.g., difficulty level or problem type) as an individual arm. We leverage the absolute advantage from policy gradient methods as a proxy measure for immediate learning gain. At each training step, the curriculum policy selects categories to maximize this reward signal and is updated using the TD(0) method. Across three distinct reasoning domains: planning, inductive reasoning, and mathematics, our experiments demonstrate that SEC significantly improves models' reasoning capabilities, enabling better generalization to harder, out-of-distribution test problems. Additionally, our approach achieves better skill balance when fine-tuning simultaneously on multiple reasoning domains. These findings highlight SEC as a promising strategy for RL fine-tuning of LLMs.

Large reasoning models (LRMs), such as OpenAI o1 and DeepSeek-R1, have significantly enhanced their reasoning capabilities by generating longer chains of thought, demonstrating outstanding performance across a variety of tasks. However, this performance gain comes at the cost of a substantial increase in redundant reasoning during the generation process, leading to high computational overhead and exacerbating the issue of overthinking. Although numerous existing approaches aim to address the problem of overthinking, they often rely on external interventions. In this paper, we propose a novel framework, Self-Braking Tuning (SBT), which tackles overthinking from the perspective of allowing the model to regulate its own reasoning process, thus eliminating the reliance on external control mechanisms. We construct a set of overthinking identification metrics based on standard answers and design a systematic method to detect redundant reasoning. This method accurately identifies unnecessary steps within the reasoning trajectory and generates training signals for learning self-regulation behaviors. Building on this foundation, we develop a complete strategy for constructing data with adaptive reasoning lengths and introduce an innovative braking prompt mechanism that enables the model to naturally learn when to terminate reasoning at an appropriate point. Experiments across mathematical benchmarks (AIME, AMC, MATH500, GSM8K) demonstrate that our method reduces token consumption by up to 60% while maintaining comparable accuracy to unconstrained models.

The rapid advancement of Large Language Models (LLMs) has stimulated interest in multi-agent collaboration for addressing complex medical tasks. However, the practical advantages of multi-agent collaboration approaches remain insufficiently understood. Existing evaluations often lack generalizability, failing to cover diverse tasks reflective of real-world clinical practice, and frequently omit rigorous comparisons against both single-LLM-based and established conventional methods. To address this critical gap, we introduce MedAgentBoard, a comprehensive benchmark for the systematic evaluation of multi-agent collaboration, single-LLM, and conventional approaches. MedAgentBoard encompasses four diverse medical task categories: (1) medical (visual) question answering, (2) lay summary generation, (3) structured Electronic Health Record (EHR) predictive modeling, and (4) clinical workflow automation, across text, medical images, and structured EHR data. Our extensive experiments reveal a nuanced landscape: while multi-agent collaboration demonstrates benefits in specific scenarios, such as enhancing task completeness in clinical workflow automation, it does not consistently outperform advanced single LLMs (e.g., in textual medical QA) or, critically, specialized conventional methods that generally maintain better performance in tasks like medical VQA and EHR-based prediction. MedAgentBoard offers a vital resource and actionable insights, emphasizing the necessity of a task-specific, evidence-based approach to selecting and developing AI solutions in medicine. It underscores that the inherent complexity and overhead of multi-agent collaboration must be carefully weighed against tangible performance gains. All code, datasets, detailed prompts, and experimental results are open-sourced at https://medagentboard.netlify.app/.

Test-time scaling (TTS) has proven effective in enhancing the reasoning capabilities of large language models (LLMs). Verification plays a key role in TTS, simultaneously influencing (1) reasoning performance and (2) compute efficiency, due to the quality and computational cost of verification. In this work, we challenge the conventional paradigms of verification, and make the first attempt toward systematically investigating the impact of verification granularity-that is, how frequently the verifier is invoked during generation, beyond verifying only the final output or individual generation steps. To this end, we introduce Variable Granularity Search (VG-Search), a unified algorithm that generalizes beam search and Best-of-N sampling via a tunable granularity parameter g. Extensive experiments with VG-Search under varying compute budgets, generator-verifier configurations, and task attributes reveal that dynamically selecting g can improve the compute efficiency and scaling behavior. Building on these findings, we propose adaptive VG-Search strategies that achieve accuracy gains of up to 3.1\% over Beam Search and 3.6\% over Best-of-N, while reducing FLOPs by over 52\%. We will open-source the code to support future research.

Distributed inference of large language models (LLMs) can introduce overheads of up to 20% even over GPUs connected via high-speed interconnects such as NVLink. Multiple techniques have been proposed to mitigate these overheads by decomposing computations into finer-grained tasks and overlapping communication with sub-tasks as they complete. However, fine-grained decomposition of a large computation into many smaller computations on GPUs results in overheads. Furthermore, the communication itself uses many streaming multiprocessors (SMs), adding to the overhead. We present TokenWeave to address these challenges. TokenWeave proposes a Token-Splitting technique that divides the tokens in the inference batch into two approximately equal subsets in a wave-aware manner. The communication of one subset is then overlapped with the computation of the other. In addition, TokenWeave optimizes the order of the layer normalization computation with respect to communication operations and implements a novel fused AllReduce--RMSNorm kernel that carefully leverages Multimem instruction support available on Hopper and Blackwell NVIDIA GPUs. These optimizations allow TokenWeave to perform communication and RMSNorm using only 2-8 SMs. Moreover, our kernel enables the memory-bound RMSNorm to be overlapped with the other batch's computation, providing additional gains. Our evaluations demonstrate up to 1.29x speedup in latency and 1.26x higher throughput across multiple models and workloads. In several settings, TokenWeave results in better performance compared to an equivalent model with all communication removed.

Generative artificial intelligence (Gen AI) systems represent a critical technology with far-reaching implications across multiple domains of society. However, their deployment entails a range of risks and challenges that require careful evaluation. To date, there has been a lack of comprehensive, interdisciplinary studies offering a systematic comparison between open-source and proprietary (closed) generative AI systems, particularly regarding their respective advantages and drawbacks. This study aims to: i) critically evaluate and compare the characteristics, opportunities, and challenges of open and closed generative AI models; and ii) propose foundational elements for the development of an Open, Public, and Safe Gen AI framework. As a methodology, we adopted a combined approach that integrates three methods: literature review, critical analysis, and comparative analysis. The proposed framework outlines key dimensions, openness, public governance, and security, as essential pillars for shaping the future of trustworthy and inclusive Gen AI. Our findings reveal that open models offer greater transparency, auditability, and flexibility, enabling independent scrutiny and bias mitigation. In contrast, closed systems often provide better technical support and ease of implementation, but at the cost of unequal access, accountability, and ethical oversight. The research also highlights the importance of multi-stakeholder governance, environmental sustainability, and regulatory frameworks in ensuring responsible development.

Agents are predominantly evaluated and optimized via task success metrics, which are coarse, rely on manual design from experts, and fail to reward intermediate emergent behaviors. We propose **AutoLibra**, a framework for agent evaluation, that transforms open-ended human feedback *e.g.* "If you find that the button is disabled, don't click it again", or "This agent has too much autonomy to decide what to do on its own" into metrics for evaluating fine-grained behaviors in agent trajectories. AutoLibra accomplishes this by grounding feedback to an agent's behavior, clustering similar positive and negative behaviors, and creating concrete metrics with clear definitions and concrete examples, which can be used for prompting LLM-as-a-Judge as evaluators. We further propose two meta metrics to evaluate the alignment of a set of (induced) metrics with open feedback: "coverage" and "redundancy". Through optimizing these meta-metrics, we experimentally demonstrate AutoLibra's ability to induce more concrete agent evaluation metrics than the ones proposed in previous agent evaluation benchmarks and discover new metrics to analyze agents. We also present two applications of AutoLibra in agent improvement: First, we show that AutoLibra serve human prompt engineers for diagonalize agent failures and improve prompts iterative. Moreover, we find that AutoLibra can induce metrics for automatic optimization for agents, which makes agents improve through self-regulation. Our results suggest that AutoLibra is a powerful task-agnostic tool for evaluating and improving language agents.

To what extent can entire books be extracted from LLMs? Using the Llama 3 70B family of models, and the "prefix-prompting" extraction technique, we were able to auto-regressively reconstruct, with a very high level of similarity, one entire book (Alice's Adventures in Wonderland) from just the first 500 tokens. We were also able to obtain high extraction rates on several other books, piece-wise. However, these successes do not extend uniformly to all books. We show that extraction rates of books correlate with book popularity and thus, likely duplication in the training data. We also confirm the undoing of mitigations in the instruction-tuned Llama 3.1, following recent work (Nasr et al., 2025). We further find that this undoing comes from changes to only a tiny fraction of weights concentrated primarily in the lower transformer blocks. Our results provide evidence of the limits of current regurgitation mitigation strategies and introduce a framework for studying how fine-tuning affects the retrieval of verbatim memorization in aligned LLMs.

Recently, Large Language Models (LLMs) have dominated much of the artificial intelligence scene with their ability to process and generate natural languages. However, the majority of LLM research and development remains English-centric, leaving low-resource languages such as those in the Southeast Asian (SEA) region under-represented. To address this representation gap, we introduce Llama-SEA-LION-v3-8B-IT and Gemma-SEA-LION-v3-9B-IT, two cutting-edge multilingual LLMs designed for SEA languages. The SEA-LION family of LLMs supports 11 SEA languages, namely English, Chinese, Indonesian, Vietnamese, Malay, Thai, Burmese, Lao, Filipino, Tamil, and Khmer. Our work leverages large-scale multilingual continued pre-training with a comprehensive post-training regime involving multiple stages of instruction fine-tuning, alignment, and model merging. Evaluation results on multilingual benchmarks indicate that our models achieve state-of-the-art performance across LLMs supporting SEA languages. We open-source the models to benefit the wider SEA community.

The use of language models for automatically evaluating long-form text (LLM-as-a-judge) is becoming increasingly common, yet most LLM judges are optimized exclusively for English, with strategies for enhancing their multilingual evaluation capabilities remaining largely unexplored in the current literature. This has created a disparity in the quality of automatic evaluation methods for non-English languages, ultimately hindering the development of models with better multilingual capabilities. To bridge this gap, we introduce M-Prometheus, a suite of open-weight LLM judges ranging from 3B to 14B parameters that can provide both direct assessment and pairwise comparison feedback on multilingual outputs. M-Prometheus models outperform state-of-the-art open LLM judges on multilingual reward benchmarks spanning more than 20 languages, as well as on literary machine translation (MT) evaluation covering 4 language pairs. Furthermore, M-Prometheus models can be leveraged at decoding time to significantly improve generated outputs across all 3 tested languages, showcasing their utility for the development of better multilingual models. Lastly, through extensive ablations, we identify the key factors for obtaining an effective multilingual judge, including backbone model selection and training on synthetic multilingual feedback data instead of translated data. We release our models, training dataset, and code.