Healthcare AI's next test is integration While advanced AI excels at processing clinical data, healthcare's true test lies in overcoming deeply fragmented administrative workflows. The entrance of major AI companies into healthcare is a meaningful and welcome development, accelerating the technical foundation available to the industry. Their models are increasingly capable of processing long clinical records, interpreting complex terminology, comparing documentation against evidence and generating coherent summaries from large volumes of information. For clinicians, operators, and administrative teams who spend significant time searching through fragmented data, these advances are helping reduce cognitive burden and make high-value information easier to access. But healthcare leaders should not confuse model capability with operational capability. Healthcare's administrative challenges are caused by fragmented information, fragmented workflows, and fragmented accountability, not a lack of information.

That's a major factor in how well models do on the most famous puzzle-based benchmark, ARC-AGI. These problems require you to infer abstract, general rules from a set of examples. Models do better on ARC puzzles when they receive each grid not as an image but as a string of numbers that encodes the color of each cell. Research suggests that even when models answer ARC-AGI questions correctly, they often do so using byzantine and non-generalizable rules, whereas humans draw on simple visual concepts. Despite these disadvantages, models have gotten quite good at ARC-AGI over the past year, but some puzzles--such as the one printed here--still stump them.

The 35th International Joint Conference on Artificial Intelligence and the 29th European Conference on Artificial Intelligence (IJACI-ECAI 2026) will be held from 15-21 August, in Bremen, Germany. The conference will feature workshops and tutorials, keynote and invited talks, technical presentations, posters, diversity and inclusion event, outreach, and more. Experts from research, practice, public institutions and civil society discuss how AI is changing key areas of everyday life in moderated panel discussions. The AI Lounges will be held in German. The tutorials will also take place from 15-17 August.

'Patients will need doctors who can stand apart from the machine long enough to know when it is wrong, incomplete, or right for the wrong reason.' 'Patients will need doctors who can stand apart from the machine long enough to know when it is wrong, incomplete, or right for the wrong reason.' What happens when medical students rely on AI - and never develop their own judgment? AI's danger isn't just in experts losing the ability to reason. It's that trainees may never learn how to do so in the first place I n healthcare, there's growing concern over doctors becoming less clinically adept as they increasingly rely on AI tools.

CogTwin is a hybrid cognitive architecture framework designed to bring autonomous reasoning and real-time adaptation to digital twin systems. Presented at IJCAI 2025, this work aims to advance the state of digital twin technology by addressing key gaps in autonomy, cognition, and real-time decision-making. Digital twin technology has transformed how complex systems are managed, from smart cities to industrial processes. However, most current digital twins remain fundamentally reactive: they rely on pre-programmed rules and static data-driven models, and therefore struggle when confronted with unforeseen events or evolving conditions. Real-time learning, reasoning, and adaptation - hallmarks of human cognition - are largely absent.

We deploy a simple into our everyday lives as search engines (Jin et al., 2025; statistical framework based on risk control (Angelopoulos Xiong et al., 2024), coding assistants (Zhao et al., 2023), et al., 2022) that converts any safety signal into a binary and companions (Zhang et al., 2025a). As their applicability grows, so does the potential harm caused by malicious decision rule, and offers statistical guarantees on the false LLM outputs. Despite remarkable performance across a alarm or missed detection rate. The framework is universally applicable to different monitoring purposes and can leverage wide range of tasks, LLMs remain prone to generating halarbitrary proxy signals. Through experiments on mathematlucinated, factually incorrect (Ravichander et al., 2025), or ical problem solving and red teaming conversations, we harmful output (Yu et al., 2025) when deployed.

To answer this, we introduce Tropical Attention, an attention mechanism grounded in tropical geometry that lifts the attention kernel into tropical projective space, where reasoning is piecewise-linear and 1-Lipschitz, thus preserving the polyhedral decision structure inherent to combinatorial reasoning. We prove that multi-head Tropical Attention (MHTA) stacks universally approximate tropical circuits and realize tropical transitive closure through composition, achieving polynomial resource bounds without invoking recurrent mechanisms. These guarantees explain why the induced polyhedral decision boundaries remain sharp and scale-invariant, rather than smoothed by Softmax. Empirically, we show that Tropical Attention delivers stronger out-of-distribution generalization in both length and value, with high robustness against perturbative noise, and substantially faster inference with fewer parameters compared to Softmax-based and recurrent attention baselines, respectively.

Scientific reasoning is an increasingly important capability of large language models, yet improving the robustness and efficiency of training such reasoning remains a key open challenge. We study this problem in instruction-based molecular optimization, where answer-only supervised fine-tuning (SFT) collapses multi-step reasoning and reinforcement learning with verifiable rewards (RLVR) suffers from sparse feedback. Reference-guided Policy Optimization (RePO) mitigates both by anchoring policy updates to dataset-provided references, but its effectiveness is tightly coupled to reference quality: weak or misaligned references impose a performance ceiling. To overcome this ceiling, we propose active reasoning, a paradigm in which the policy actively decides, on a per-instance basis, when to imitate a reference and when to reinforce its own discoveries, while continuously upgrading what it imitates. We instantiate this paradigm as Active Group Relative Policy Optimization (Active-GRPO), realized through two coupled mechanisms: active imitate-reinforce and active referencing. The former performs imitation learning when the reference still outperforms the policy's own candidates, and shifts to self-improvement via reinforcement learning once the policy has generated molecules that surpass the reference. The latter continuously upgrades the reference itself by replacing it with the best policy-generated candidate discovered so far, progressively raising the imitation target and ensuring that reference guidance remains informative--rather than restrictive--throughout training. Across TOMG-Bench MOLOPT, Active-GRPO improves average SR Sim from 0.0959 for GRPO and 0.1665 for RePO to 0.1773 under matched three-seed evaluation, with statistically significant gains on LogP, MR, and QED.

Self-evolution offers a scalable path to stronger reasoning: a pretrained language model improves itself with only minimal external supervision. Yet existing methods either depend on extensively curated or teacher-generated training data, or, when the generator runs unsupervised, reward it by a difficulty heuristic that need not improve the solver. We introduce INFUSER, an iterative co-training framework with two co-evolving roles: a Generator that drafts questions and reference golden answers from a pool of unstructured, automatically collected documents, and a Solver that improves by training on them. The solver is trained with standard correctness rewards against the generator-provided answers, while the generator is rewarded by an optimizer-aware influence score that measures whether each proposed question would actually improve the solver on the target distribution. Because this continuous, noisy influence score is poorly served by standard GRPO, we propose DuGRPO, a dual-normalized variant of GRPO, for generator training. Together, these turn the document pool into an adaptive curriculum that favors questions useful to the current solver, not just hard ones. On Qwen3-8B-Base, INFUSER outperforms strong self-evolution baselines with over 20% relative improvement on Olympiad and SuperGPQA benchmarks, and an 8B INFUSER co-evolving generator outperforms a frozen 32B thinking generator on math and coding. Ablations confirm each design choice is necessary, and two extensions, applying INFUSER to an instruction-finetuned anchor and augmenting it with rule-verifiable RLVR data, further demonstrate the flexibility and generalizability of the framework. Code is available at https://github.com/FFishy-git/INFUSER.

Charts are high-density visualization carriers for complex data, serving as a crucial medium for information extraction and analysis. Automated chart understanding poses significant challenges to existing multimodal large language models (MLLMs) due to the need for precise and complex visual reasoning. Current step-by-step reasoning models primarily focus on text-based logical reasoning for chart understanding. However, they struggle to refine or correct their reasoning when errors stem from flawed visual understanding, as they lack the ability to leverage multimodal interaction for deeper comprehension. Inspired by human cognitive behavior, we propose ChartSketcher, a multimodal feedback-driven step-by-step reasoning method designed to address these limitations. ChartSketcher is a chart understanding model that employs Sketch-CoT, enabling MLLMs to annotate intermediate reasoning steps directly onto charts using a programmatic sketching library, iteratively feeding these visual annotations back into the reasoning process. This mechanism enables the model to visually ground its reasoning and refine its understanding over multiple steps. We employ a two-stage training strategy: a cold start phase to learn sketch-based reasoning patterns, followed by off-policy reinforcement learning to enhance reflection and generalization. Experiments demonstrate that ChartSketcher achieves promising performance on chart understanding benchmarks and general vision tasks, providing an interactive and interpretable approach to chart comprehension.