Agentic Transformers Provably Learn to Search via Reinforcement Learning

Tree search is a central abstraction behind many language-agent reasoning and decision-making tasks: agents must explore actions, remember failures, and backtrack toward promising alternatives. Yet, we lack a theoretical understanding of how transformer-based policies acquire such search capabilities from the training dynamics of reinforcement learning (RL). We study this question in a stochastic $k$-ary tree environment, where an agentic transformer observes only its trajectory history through interaction and receives a terminal reward for reaching a hidden leaf goal node. We first construct a two-head transformer that implements randomized depth-first search (DFS): one head tracks previous actions, while the other detects failure outcomes and triggers backtracking. We then analyze the training dynamics of policy gradient under a depth-wise curriculum, showing that this same DFS mechanism emerges in stages from sparse reinforcement feedback without expert demonstrations. The resulting policy exhibits depth generalization: after training only on depth-$1$ and depth-$2$ trees, it succeeds on deeper full trees. We further show that, under imbalanced goal distributions, discounting the return leads to a ranked DFS policy that prioritizes higher-probability branches. Overall, our results identify a mechanistic normal form for transformer-based search, in which attention heads specialize and cooperate to extract decision-relevant traces from context and convert them into agentic action selection via RL training.

How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions

AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of 20,574 coding-agent sessions from 1,639 repositories across IDE and CLI workflows. We operationalize misalignment as a breakdown made visible through developer pushback, and annotate each episode along four axes: form, cause, cost, and resolution. We identify seven recurring forms, spanning how agents read projects, interpret developer intent, follow rules, bound their actions, implement and execute code, and report progress. 90.50\% of episodes impose effort and trust costs rather than irreversible system damage, yet 91.49\% of visible resolutions still require explicit user correction. Misalignment patterns also differ across IDE and CLI settings, persist across adjacent sessions, and shift over time: while overall rates decline, constraint violations and inaccurate self-reporting grow in share. Our findings inform the design of training, evaluation, and interfaces for keeping coding agents aligned with real developer workflows.

Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards

The open-ended generation in LLMs usually requires multi-dimensional rubrics to adequately assess quality and guide the improvement of reinforcement learning. However, a critical dilemma inherent in this training paradigm is the imbalanced reward polarization along different rubric dimensions. Under this bottleneck, even if LLMs achieve relatively high rewards after training, they may still exhibit severe deficiencies in certain dimensions, leading to a direct deterioration in user experience. To address this problem, we propose Focal Reward, a novel objective to automatically balance the training of reinforcement learning under rubric-based rewards. Specifically, we first leverage an inverse reward projection mechanism to estimate the saturation degree of each criterion in the rubric, which forms the basis to calibrate the reward direction. Then, the final objective is designed with an automatically reweighting coefficient for each criterion to achieve the fine-grained balancing. Extensive experiments across three model scales and six benchmarks demonstrate that our Focal Reward method outperforms the strongest static aggregation baseline in all 18 model-benchmark comparisons. Rollout, mechanism, and ablation analyses further show that these gains arise from online, saturation-aware reallocation toward rubrics that still have room for improvement.

OphMAE: Bridging Volumetric and Planar Imaging with a Foundation Model for Adaptive Ophthalmological Diagnosis

The advent of foundation models has heralded a new era in medical artificial intelligence (AI), enabling the extraction of generalizable representations from large-scale unlabeled datasets. However, current ophthalmic AI paradigms are predominantly constrained to single-modality inference, thereby creating a dissonance with clinical practice where diagnosis relies on the synthesis of complementary imaging modalities. Furthermore, the deployment of high-performance AI in resource-limited settings is frequently impeded by the unavailability of advanced three-dimensional imaging hardware. Here, we present the Ophthalmic multimodal Masked Autoencoder (OphMAE), a multi-imaging foundation model engineered to synergize the volumetric depth of 3D Optical Coherence Tomography (OCT) with the planar context of 2D en face OCT. By implementing a novel cross-modal fusion architecture and a unique adaptive inference mechanism, OphMAE was pre-trained on a massive dataset with of 183,875 paired OCT images derived from 32,765 patients. In a rigorous benchmark encompassing 17 diverse diagnostic tasks with 48,340 paired OCT images from 8,191 patients, the model demonstrated state-of-the-art performance, achieving an Area Under the Curve (AUC) of 96.9% for Age-related Macular Degeneration (AMD) and 97.2% for Diabetic Macular Edema (DME), consistently surpassing existing single-modal and multimodal foundation models. Crucially, OphMAE exhibits robust engineering adaptability: it maintains high diagnostic accuracy, such as 93.7\% AUC for AMD, even when restricted to single-modality 2D inputs, and demonstrates exceptional data efficiency by retaining 95.7% AUC with as few as 500 labeled samples. This work establishes a scalable and adaptable framework for ophthalmic AI, ensuring robust performance across different tasks.

SAIL: Structure-Aware Interpretable Learning for Anatomy-Aligned Post-hoc Explanations in OCT

Optical coherence tomography (OCT), a commonly used retinal imaging modality, plays a central role in retinal disease diagnosis by providing high-resolution visualization of retinal layers. While deep learning (DL) has achieved expert-level accuracy in OCT-based retinal disease detection, its "black box" nature poses challenges for clinical adoption, where explainability is essential for clinical trust and regulatory approval. Existing post-hoc explainable AI (XAI) methods often struggle to delineate fine-grained lesion structures, respect anatomical boundaries, or suppress noise, limiting the trustworthiness of their explanations. To bridge these gaps, we propose a Structure-Aware Interpretable Learning (SAIL) framework that integrates retinal anatomical priors at the representation level and couples them with semantic features via a fusion design. Without modifying standard post-hoc explainability methods, this representation yields sharper and more anatomically aligned attribution maps. Comprehensive experiments on diverse OCT datasets demonstrate that our structure-aware method consistently enhances interpretability, producing clinically meaningful and anatomy-aware explanations. Ablation studies further show that strong interpretability requires both structural priors and semantic features, and that properly fusing the two is critical to achieve the best explanation quality. Together, these results highlight structure-aware representations as a key step toward reliable explainability in OCT.

Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment

Modern clinical practice increasingly depends on reasoning over heterogeneous, evolving, and incomplete patient data. Although recent advances in multimodal foundation models have improved performance on various clinical tasks, most existing models remain static, opaque, and poorly aligned with real-world clinical workflows. We present Cerebra, an interactive multi-agent AI team that coordinates specialized agents for EHR, clinical notes, and medical imaging analysis. These outputs are synthesized into a clinician-facing dashboard that combines visual analytics with a conversational interface, enabling clinicians to interrogate predictions and contextualize risk at the point of care. Cerebra supports privacy-preserving deployment by operating on structured representations and remains robust when modalities are incomplete. We evaluated Cerebra using a massive multi-institutional dataset spanning 3 million patients from four independent healthcare systems. Cerebra consistently outperformed both state-of-the-art single-modality models and large multimodal language model baselines. In dementia risk prediction, it achieved AUROCs up to 0.80, compared with 0.74 for the strongest single-modality model and 0.68 for language model baselines. For dementia diagnosis, it achieved an AUROC of 0.86, and for survival prediction, a C-index of 0.81. In a reader study with experienced physicians, Cerebra significantly improved expert performance, increasing accuracy by 17.5 percentage points in prospective dementia risk estimation. These results demonstrate Cerebra's potential for interpretable, robust decision support in clinical care.

A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment

Modern clinical practice increasingly depends on reasoning over heterogeneous, evolving, and incomplete patient data. Although recent advances in multimodal foundation models have improved performance on various clinical tasks, most existing models remain static, opaque, and poorly aligned with real-world clinical workflows. We present Cerebra, an interactive multi-agent AI team that coordinates specialized agents for EHR, clinical notes, and medical imaging analysis. These outputs are synthesized into a clinician-facing dashboard that combines visual analytics with a conversational interface, enabling clinicians to interrogate predictions and contextualize risk at the point of care. Cerebra supports privacy-preserving deployment by operating on structured representations and remains robust when modalities are incomplete. We evaluated Cerebra using a massive multi-institutional dataset spanning 3 million patients from four independent healthcare systems. Cerebra consistently outperformed both state-of-the-art single-modality models and large multimodal language model baselines. In dementia risk prediction, it achieved AUROCs up to 0.80, compared with 0.74 for the strongest single-modality model and 0.68 for language model baselines. For dementia diagnosis, it achieved an AUROC of 0.86, and for survival prediction, a C-index of 0.81. In a reader study with experienced physicians, Cerebra significantly improved expert performance, increasing accuracy by 17.5 percentage points in prospective dementia risk estimation. These results demonstrate Cerebra's potential for interpretable, robust decision support in clinical care.

AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents

Long-horizon GUI agents are a key step toward real-world deployment, yet effective interaction memory under prevailing paradigms remains under-explored. Replaying full interaction sequences is redundant and amplifies noise, while summaries often erase dependency-critical information and traceability. We present AndroTMem, a diagnostic framework for anchored memory in long-horizon Android GUI agents. Its core benchmark, AndroTMem-Bench, comprises 1,069 tasks with 34,473 interaction steps (avg. 32.1 per task, max. 65). We evaluate agents with TCR (Task Complete Rate), focusing on tasks whose completion requires carrying forward critical intermediate state; AndroTMem-Bench is designed to enforce strong step-to-step causal dependencies, making sparse yet essential intermediate states decisive for downstream actions and centering interaction memory in evaluation. Across open- and closed-source GUI agents, we observe a consistent pattern: as interaction sequences grow longer, performance drops are driven mainly by within-task memory failures, not isolated perception errors or local action mistakes. Guided by this diagnosis, we propose Anchored State Memory (ASM), which represents interaction sequences as a compact set of causally linked intermediate-state anchors to enable subgoal-targeted retrieval and attribution-aware decision making. Across multiple settings and 12 evaluated GUI agents, ASM consistently outperforms full-sequence replay and summary-based baselines, improving TCR by 5%-30.16% and AMS by 4.93%-24.66%, indicating that anchored, structured memory effectively mitigates the interaction-memory bottleneck in long-horizon GUI tasks. The code, benchmark, and related resources are publicly available at [https://github.com/CVC2233/AndroTMem](https://github.com/CVC2233/AndroTMem).

On the Learnability of Offline Model-Based Optimization: A Ranking Perspective

Offline model-based optimization (MBO) seeks to discover high-performing designs using only a fixed dataset of past evaluations. Most existing methods rely on learning a surrogate model via regression and implicitly assume that good predictive accuracy leads to good optimization performance. In this work, we challenge this assumption and study offline MBO from a learnability perspective. We argue that offline optimization is fundamentally a problem of ranking high-quality designs rather than accurate value prediction. Specifically, we introduce an optimization-oriented risk based on ranking between near-optimal and suboptimal designs, and develop a unified theoretical framework that connects surrogate learning to final optimization. We prove the theoretical advantages of ranking over regression, and identify distributional mismatch between the training data and near-optimal designs as the dominant error. Inspired by this, we design a distribution-aware ranking method to reduce this mismatch. Empirical results across various tasks show that our approach outperforms twenty existing methods, validating our theoretical findings. Additionally, both theoretical and empirical results reveal intrinsic limitations in offline MBO, showing a regime in which no offline method can avoid over-optimistic extrapolation.

Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations

Harnessing the full potential of visually-rich documents requires retrieval systems that understand not just text, but intricate layouts, a core challenge in Visual Document Retrieval (VDR). The prevailing multi-vector architectures, while powerful, face a crucial storage bottleneck that current optimization strategies, such as embedding merging, pruning, or using abstract tokens, fail to resolve without compromising performance or ignoring vital layout cues. To address this, we introduce ColParse, a novel paradigm that leverages a document parsing model to generate a small set of layout-informed sub-image embeddings, which are then fused with a global page-level vector to create a compact and structurally-aware multi-vector representation. Extensive experiments demonstrate that our method reduces storage requirements by over 95% while simultaneously yielding significant performance gains across numerous benchmarks and base models. ColParse thus bridges the critical gap between the fine-grained accuracy of multi-vector retrieval and the practical demands of large-scale deployment, offering a new path towards efficient and interpretable multimodal information systems.