Global optimization of expensive, potentially gradient-free functions has long been a critical component of many complex problems in science and engineering.

We introduce SkyRL-Agent, a framework for efficient, multi-turn, long-horizon agent training and evaluation. It provides efficient asynchronous dispatching, lightweight tool integration, and flexible backend interoperability, enabling seamless use with existing RL frameworks such as SkyRL-train, VeRL, and Tinker. Using SkyRL-Agent, we train SA-SWE-32B, a software engineering agent trained from Qwen3-32B (24.4% Pass@1) purely with reinforcement learning. We introduce two key components: an optimized asynchronous pipeline dispatcher that achieves a 1.55x speedup over naive asynchronous batching, and a tool-enhanced training recipe leveraging an AST-based search tool to facilitate code navigation, boost rollout Pass@K, and improve training efficiency. Together, these optimizations enable SA-SWE-32B to reach 39.4% Pass@1 on SWE-Bench Verified with more than 2x cost reduction compared to prior models reaching similar performance. Despite being trained solely on SWE tasks, SA-SWE-32B generalizes effectively to other agentic tasks, including Terminal-Bench, BrowseComp-Plus, and WebArena. We further demonstrate SkyRL-Agent's extensibility through case studies on deep research, computer use, and memory agents, each trained using a different training backend.

We propose MedBayes-Lite, a lightweight Bayesian enhancement for transformer-based clinical language models designed to produce reliable, uncertainty-aware predictions. Although transformers show strong potential for clinical decision support, they remain prone to overconfidence, especially in ambiguous medical cases where calibrated uncertainty is critical. MedBayes-Lite embeds uncertainty quantification directly into existing transformer pipelines without any retraining or architectural rewiring, adding no new trainable layers and keeping parameter overhead under 3 percent. The framework integrates three components: (i) Bayesian Embedding Calibration using Monte Carlo dropout for epistemic uncertainty, (ii) Uncertainty-Weighted Attention that marginalizes over token reliability, and (iii) Confidence-Guided Decision Shaping inspired by clinical risk minimization. Across biomedical QA and clinical prediction benchmarks (MedQA, PubMedQA, MIMIC-III), MedBayes-Lite consistently improves calibration and trustworthiness, reducing overconfidence by 32 to 48 percent. In simulated clinical settings, it can prevent up to 41 percent of diagnostic errors by flagging uncertain predictions for human review. These results demonstrate its effectiveness in enabling reliable uncertainty propagation and improving interpretability in medical AI systems.

In this paper, we present gfnx, a fast and scalable package for training and evaluating Generative Flow Networks (GFlowNets) written in JAX. gfnx provides an extensive set of environments and metrics for benchmarking, accompanied with single-file implementations of core objectives for training GFlowNets. We include synthetic hypergrids, multiple sequence generation environments with various editing regimes and particular reward designs for molecular generation, phylogenetic tree construction, Bayesian structure learning, and sampling from the Ising model energy. Across different tasks, gfnx achieves significant wall-clock speedups compared to Pytorch-based benchmarks (such as torchgfn library) and author implementations. For example, gfnx achieves up to 55 times speedup on CPU-based sequence generation environments, and up to 80 times speedup with the GPU-based Bayesian network structure learning setup. Our package provides a diverse set of benchmarks and aims to standardize empirical evaluation and accelerate research and applications of GFlowNets. The library is available on GitHub (https://github.com/d-tiapkin/gfnx) and on pypi (https://pypi.org/project/gfnx/). Documentation is available on https://gfnx.readthedocs.io.

Efficient and lightweight adaptation of pre-trained Vision-Language Models (VLMs) to downstream tasks through collaborative interactions between local clients and a central server is a rapidly emerging research topic in federated learning. Existing adaptation algorithms are typically trained iteratively, which incur significant communication costs and increase the susceptibility to potential attacks. Motivated by the one-shot federated training techniques that reduce client-server exchanges to a single round, developing a lightweight one-shot federated VLM adaptation method to alleviate these issues is particularly attractive. However, current one-shot approaches face certain challenges in adapting VLMs within federated settings: (1) insufficient exploitation of the rich multimodal information inherent in VLMs; (2) lack of specialized adaptation strategies to systematically handle the severe data heterogeneity; and (3) requiring additional training resource of clients or server. To bridge these gaps, we propose a novel Training-free One-shot Federated Adaptation framework for VLMs, named TOFA. To fully leverage the generalizable multimodal features in pre-trained VLMs, TOFA employs both visual and textual pipelines to extract task-relevant representations. In the visual pipeline, a hierarchical Bayesian model learns personalized, class-specific prototype distributions. For the textual pipeline, TOFA evaluates and globally aligns the generated local text prompts for robustness. An adaptive weight calibration mechanism is also introduced to combine predictions from both modalities, balancing personalization and robustness to handle data heterogeneity. Our method is training-free, not relying on additional training resources on either the client or server side. Extensive experiments across 9 datasets in various federated settings demonstrate the effectiveness of the proposed TOFA method.

Wearable sensor technologies and deep learning are transforming healthcare management. Yet, most health sensing studies focus narrowly on physical chronic diseases. This overlooks the critical need for joint assessment of comorbid physical chronic diseases and depression, which is essential for collaborative chronic care. We conceptualize multi-disease assessment, including both physical diseases and depression, as a multi-task learning (MTL) problem, where each disease assessment is modeled as a task. This joint formulation leverages inter-disease relationships to improve accuracy, but it also introduces the challenge of double heterogeneity: chronic diseases differ in their manifestation (disease heterogeneity), and patients with the same disease show varied patterns (patient heterogeneity). To address these issues, we first adopt existing techniques and propose a base method. Given the limitations of the base method, we further propose an Advanced Double Heterogeneity-based Multi-Task Learning (ADH-MTL) method that improves the base method through three innovations: (1) group-level modeling to support new patient predictions, (2) a decomposition strategy to reduce model complexity, and (3) a Bayesian network that explicitly captures dependencies while balancing similarities and differences across model components. Empirical evaluations on real-world wearable sensor data demonstrate that ADH-MTL significantly outperforms existing baselines, and each of its innovations is shown to be effective. This study contributes to health information systems by offering a computational solution for integrated physical and mental healthcare and provides design principles for advancing collaborative chronic disease management across the pre-treatment, treatment, and post-treatment phases.

Robots today often miss a key ingredient of truly intelligent behavior: the ability to reflect on their own cognitive processes and decisions. In humans, this self-monitoring or metacognition is crucial for learning, decision making and problem solving. For instance, they can evaluate how confident they are in performing a task, thus regulating their own behavior and allocating proper resources. Taking inspiration from neuroscience, we propose a robot metacognition architecture centered on confidence (a second-order judgment on decisions) and we demonstrate it on the use case of autonomous tool invention. We propose the use of confidence as a metacognitive measure within the robot decision making scheme. Confidence-informed robots can evaluate the reliability of their decisions, improving their robustness during real-world physical deployment. This form of robotic metacognition emphasizes embodied action monitoring as a means to achieve better informed decisions. We also highlight potential applications and research directions for robot metacognition.

Controlled language generation conditions text on sequence-level constraints (for example, syntax, style, or safety). These constraints may depend on future tokens, which makes directly conditioning an autoregressive language model (LM) generally intractable. Prior work uses tractable surrogates such as hidden Markov models (HMMs) to approximate the distribution over continuations and adjust the model's next-token logits at decoding time. However, we find that these surrogates are often weakly context aware, which reduces query quality. We propose Learning to Look Ahead (LTLA), a hybrid approach that pairs the same base language model for rich prefix encoding with a fixed tractable surrogate model that computes exact continuation probabilities. Two efficiency pitfalls arise when adding neural context: (i) naively rescoring the prefix with every candidate next token requires a sweep over the entire vocabulary at each step, and (ii) predicting fresh surrogate parameters for each prefix, although tractable at a single step, forces recomputation of future probabilities for every new prefix and eliminates reuse. LTLA avoids both by using a single batched HMM update to account for all next-token candidates at once, and by conditioning only the surrogate's latent state prior on the LM's hidden representations while keeping the surrogate decoder fixed, so computations can be reused across prefixes. Empirically, LTLA attains higher conditional likelihood than an unconditional HMM, approximates continuation distributions for vision-language models where a standalone HMM cannot encode visual context, and improves constraint satisfaction at comparable fluency on controlled-generation tasks, with minimal inference overhead.

Large language models (LLMs) have recently demonstrated impressive capabilities across a range of reasoning and generation tasks. However, research studies have shown that LLMs lack the ability to identify causal relationships, a fundamental cornerstone of human intelligence. We first conduct an exploratory investigation of LLMs' behavior when asked to perform a causal-discovery task and find that they mostly rely on the semantic meaning of variable names, ignoring the observation data. This is unsurprising, given that LLMs were never trained to process structural datasets. To first tackle this challenge, we prompt the LLMs with the outputs of established causal discovery algorithms designed for observational datasets. These algorithm outputs effectively serve as the sufficient statistics of the observation data. However, quite surprisingly, we find that prompting the LLMs with these sufficient statistics decreases the LLMs' performance in causal discovery. To address this current limitation, we propose CARE, a framework that enhances LLMs' causal-reasoning ability by teaching them to effectively utilize the outputs of established causal-discovery algorithms through supervised fine-tuning. Experimental results show that a finetuned Qwen2.5-1.5B model produced by CARE significantly outperforms both traditional causal-discovery algorithms and state-of-the-art LLMs with over a thousand times more parameters, demonstrating effective utilization of its own knowledge and the external algorithmic clues.

I've Changed My Mind: Robots Adapting to Changing Human Goals during Collaboration Abstract --For effective human-robot collaboration, a robot must align its actions with human goals, even as they change mid-task. Prior approaches often assume fixed goals, reducing goal prediction to a one-time inference. However, in real-world scenarios, humans frequently shift goals, making it challenging for robots to adapt without explicit communication. We propose a method for detecting goal changes by tracking multiple candidate action sequences and verifying their plausibility against a policy bank. Upon detecting a change, the robot refines its belief in relevant past actions and constructs Receding Horizon Planning (RHP) trees to actively select actions that assist the human while encouraging Differentiating Actions to reveal their updated goal. We evaluate our approach in a collaborative cooking environment with up to 30 unique recipes and compare it to three comparable human goal prediction algorithms. Our method outperforms all baselines, quickly converging to the correct goal after a switch, reducing task completion time and improving collaboration efficiency. N real-world scenarios, humans often change their goals in response to evolving circumstances, new information, or spontaneous decisions. Previous work often addresses changing human goals by relying on explicit communication [1], [2], [3]. While effective, relying on communication assumes humans can and will communicate with the robot, which is often impractical due to physical, situational, or cognitive constraints [4], [5], [6], [7], [8].