Development and Preliminary Evaluation of a Conversational Agent Delivering Problem-Solving Therapy for Family Caregivers of Children With a Chronic Health Condition: Multiphase Mixed Methods Study

By: Weichao Yuwen · Liying Wang · Serena Jinchen Xie · Myra Divina · Xuehong Fan · William Kearns · Teresa M Ward

7 October 2026 at 03:00

Background: Family caregivers of children with chronic health conditions experience substantial physical and mental health burdens, including burnout, anxiety, depression, fatigue, and sleep disturbances. Despite this need, validated digital mental health tools tailored to family caregivers remain limited. AI-powered conversational agents offer a promising approach for delivering on-demand, personalized mental health support, yet development and evaluation frameworks for this population are lacking. Objective: This paper describes the iterative development and formative evaluation of COCO (Caring of Caregivers Online), a conversational agent designed for family caregivers of children with chronic health conditions. COCO integrates problem-solving therapy (PST) and motivational interviewing (MI) within a human-in-the-loop development framework that progressed from rule-based interactions to a large language model (LLM)–powered conversational agent. Methods: COCO was developed across four phases: (1) caregiver persona and dialogue development based on PST and MI; (2) usability testing of a low-fidelity prototype with standardized patients in a single session of PST; (3) usability testing of a high-fidelity prototype with caregivers in a single session of PST (n=38); (4) integration of an LLM into COCO. The Wizard-of-Oz method was used across phases 2 and 3 to collect naturalistic dialogues and refine COCO’s conversational design. In phase 3, usability of COCO was assessed using the System Usability Scale (SUS). Caregiver emotions were measured before and after the session using 6 subscales of the PANAS-X. In phase 4, GPT-4 was integrated into COCO with few-shot learning and evaluated by research team members using the caregiver personas. Descriptive statistics were used to summarize quantitative measures. The MI principles and techniques used by COCO across the 4 phases were coded using the . Results: In phase 1, 4 gold-standard dialogues were developed using caregiver personas. In phase 2, standardized patients described COCO as validating and identified its problem-solving and on-demand support as helpful for caregivers. In phase 3, COCO-Wizard-of-Oz achieved a mean SUS score of 75.6% (SD 12.9%), reflecting acceptable usability. Participants demonstrated significant improvement in negative affect, sadness, guilt, and fatigue following PST sessions (

Spatial evolution of a cachexia-promoting microenvironment in pancreatic cancer

(Multiomics OR Omics) AND (Pancreatic)

By: Yumeng Hu · Gaoyuan Lv · Hao Yuan · Zhijun Zhou · Shaobo Zhang · Yuxin Ye · Qun Chen · Yang Cai · Jingxuan Yang · Yuqing Zhang · Chao Xu · Wenyi Luo · Michael S Bronze · Courtney W Houchen · Yi-Ping Li · Jingyong Xu · Yuanyuan Zhang · Mingyang Liu · Min Li

29 September 2026 at 18:00

Cell. 2026 Sep 29:S0092-8674(26)01081-0. doi: 10.1016/j.cell.2026.09.012. Online ahead of print.

ABSTRACT

Cachexia is a major cause of morbidity in pancreatic cancer, but the cellular circuitry linking tumor progression to systemic wasting remains incompletely understood. Integrating single-cell RNA sequencing, Xenium spatial transcriptomics, multiplex immunohistochemistry, bulk transcriptomics, and functional studies across human non-cachexia, pre-cachexia, and cachexia samples, together with mouse models, we define a cachexia-associated microenvironmental niche composed of SEMA4A⁺ tumor cells, AQP9⁺ macrophages, and LOXL2⁺ cancer-associated fibroblasts. Mechanistically, SEMA4A-associated signaling promotes bone morphogenetic protein-2 (BMP2)-dependent acquisition of an AQP9-associated macrophage phenotype, and macrophage-derived CXCL8 activates LOXL2⁺ fibroblasts. LOXL2⁺ fibroblasts reciprocally enhance tumor cell FOSL1/SEMA4A signaling through exosomal N-glycosylated LOXL2. Spatial analyses demonstrate progressive enrichment of this niche with cachexia severity and association with postoperative development of cachexia in previously non-cachectic patients. These findings provide a framework linking local tumor ecosystem dynamics to cachexia progression.

PMID:42810340 | DOI:10.1016/j.cell.2026.09.012

From Fixed Keys to Readable Schemas: Small Language Models for Vehicle Agent Function Calls

cs.AI, q-bio.NC updates on arXiv.org

By: Hamed Jafarzadeh Asl · Yuanhao Yu · Vahid Partovi Nia

10 September 2026 at 12:00

arXiv:2609.09476v1 Announce Type: cross Abstract: In-vehicle assistants must translate natural-language requests into accurate vehicle function calls under strict memory and latency constraints, making small language models (SLMs) attractive for on-device deployment. For such models, a key design choice is how the available function surface is presented. Two approaches are to represent each function with a dedicated Functional Token (FT) or provide function schemas directly in the prompt. FTs enable compact inference but are restricted to functions learned during training, whereas Schema-in-Prompt (SIP) can generalize to unseen functions at the cost of longer prompts and higher inference overhead. We introduce a benchmark of 9,822 single-turn examples spanning 79 vehicle functions derived from Android Automotive, including held-out functions and requests requiring refusal. We compare both approaches under matched fine-tuning across four SLMs from 270M to 1.7B parameters. On functions seen during training, scaling provides limited benefit: the 270M model can match the 1.7B model, while the strongest overall performance occurs at 0.6B. On held-out functions, FT achieves zero accuracy by construction, whereas SIP generalizes and improves substantially with scale. On out-of-scope requests, FT can invoke an unavailable function it was trained to emit, while SIP more reliably refuses based on the functions offered. This flexibility comes with higher memory use and latency. Our theoretical analysis explains how SIP enables generalization and why longer schema contexts increase inference cost. Overall, function-surface representation, rather than model scale alone, determines the capabilities and failure modes of SLM-based vehicle function calling.

SafeCtrl-RL: Inference-Time Adaptive Behaviour Control for LLM Dialogue via RL-Driven Prompt Optimisation

cs.AI, q-bio.NC updates on arXiv.org

By: Michael Orme · Yanchao Yu · Zhiyuan Tan

26 May 2026 at 12:00

arXiv:2605.25984v1 Announce Type: cross Abstract: Ensuring safe and contextually appropriate behaviour in Large Language Models (LLMs) remains a critical challenge for real-world deployment. We present \textbf{SafeCtrl-RL}, an inference-time behavioural control framework that enables adaptive safety regulation without model retraining or parameter modification. The method formulates dialogue generation as a sequential decision process, where a reinforcement learning agent dynamically selects prompt adjustment strategies based on contextual feedback. This allows unsafe behaviours to be suppressed through iterative refinement, which we conceptualise as inference-time behavioural unlearning. Evaluated across multiple LLMs and unsafe dialogue scenarios, SafeCtrl-RL consistently improves safety and response quality, outperforms existing prompt-based optimisation methods, and achieves favourable performance--efficiency trade-offs. **Warning: This paper may contain examples of harmful language, and reader discretion is recommended.

Mendelian Randomization Analysis of the Relationship between Neurotransmitter-related Genes and Cancer: Insights from Multi-omics Data

(Multiomics OR Omics) AND (Pancreatic)

By: Quan Yuan · Yuli Xi · Hao Yu · Rongjie Ye · Neng Wang · Ge Yu · Ming Niu

21 May 2026 at 18:00

Curr Top Med Chem. 2026 May 18. doi: 10.2174/0115680266436608260406113212. Online ahead of print.

ABSTRACT

INTRODUCTION: Epidemiological studies indicate a potential link between mental disorders and cancer; however, the role of neurotransmitter-related genes (NRGs) in carcinogenesis remains unclear. In this study, we employed Mendelian randomization utilizing multi-omics data to investigate the causal effects and mechanisms of NRGs in cancer.

METHODS: We assessed the causal relationships between ten mental disorders and fourteen cancer types. NRGs were sourced from GeneCards, and transcriptome data for breast cancer (BC) were obtained from the Gene Expression Omnibus (GEO). Summary-data-based Mendelian Randomization (SMR) integrated genome-wide association study (GWAS) data with expression quantitative trait loci (eQTLs), DNA methylation QTLs (mQTLs), intestinal eQTLs, and fecal microbiota QTLs (mbQTLs). Colocalization analyses were conducted to explore the relationships between host genes and gut microbiota, with sensitivity assessments performed using two additional Mendelian randomization methods.

RESULTS: Mendelian randomization confirmed a causal association between mental disorders and BC. A meta-analysis of five BC datasets identified 821 differentially expressed genes (DEGs) among 829 non-redundant genes. SMR highlighted KRTCAP2 as a potential causal gene in blood, and cg24674445 as a significant methylation site. The expression of KRTCAP2 was found to be inversely correlated with BC, while methylation at cg24674445 downregulated KRTCAP2, suggesting that cg24674445 may promote BC progression.

DISCUSSION: This study advances beyond established epidemiological correlations by providing genetically validated evidence for a causal link between mental disorders and breast cancer. Its primary significance lies in delineating a plausible biological pathway-epigenetic regulation of neurotransmitter-related genes-that may mechanistically elucidate this connection. By integrating multi-omics data, we transition from mere association to a testable model of disease etiology, where genetic predispositions to mental illness and cancer converge upon shared regulatory mechanisms within the genome.

CONCLUSION: Multi-omics Mendelian randomization demonstrates that DNA methylation modulates the association between neurotransmitter-related genes and breast cancer.

PMID:42163732 | DOI:10.2174/0115680266436608260406113212

XPO1 inhibitor KPT-330 disrupts the core transcriptional regulatory circuitry of dedifferentiated liposarcoma by modulating the translation process

Oncogene - Issue - nature.com science feeds

By: Xiaorui Fan · Ying Zhang · Zhengming Yang · Tuan Zea Tan · Xingze Huang · Suya Zheng · Jiyang Liu · Long Xie · Ting Tao · Victor Kwanmin Lee · Chao Yu · H. Phillip Koeffler · Ye Chen · Liang Xu

16 April 2026 at 08:00

Oncogene, Published online: 16 April 2026; doi:10.1038/s41388-026-03794-w

XPO1 inhibitor KPT-330 disrupts the core transcriptional regulatory circuitry of dedifferentiated liposarcoma by modulating the translation process

GPNMB Drives Brain Metastasis by Sculpting a Pathological Endothelial-Immune Interactome

Omics In Lung

By: Xuefei Liu · Jun Tan · Chun Wu · Guanyin Huang · Yixin Cheng · Jianyang Hu · Binyu Zhang · Mao Zhao · Boxi Zhao · Jingru Lian · Shuqian Zheng · Lin Zeng · Meng Xu · Yang Xu · Shan Zeng · Hao Yu · Hui Yang · Zhixiang Zuo · Chuanyu Liu · Weineng Feng · Weinan Guo · Chunying Li · Sai-Lan Liu · Qing Liu · Feiqiu Wen · Xin Hong

13 April 2026 at 18:00

Cancer Discov. 2026 Apr 15. doi: 10.1158/2159-8290.CD-25-1663. Online ahead of print.

ABSTRACT

Brain metastases (BM) remain a devastating disease with dismal prognosis. How circulating tumor cells (CTCs) penetrate the blood brain barrier (BBB) and reprogram the brain microenvironment remain unclear. Using spatially resolved multi-omic profiling of CTCs and brain metastases, integrated with experimental and clinical analyses, we identified Glycoprotein Non-Metastatic Melanoma Protein B (GPNMB) as a CTC-secreted driver of vascular disruption and brain colonization. CBX3 upregulation induced GPNMB expression, which bound endothelial EGFR, triggering CBL-mediated ubiquitination and degradation. Attenuated EGFR signaling suppressed FTO and disrupted endothelial junctions via YTHDF2-dependent TJP1 m6A methylation. Remarkably, GPNMB-induced BBB remodeling promoted immune infiltration via CXCL12-CXCR4 axis, and induced time course-dependent T cell exhaustion within the brain microenvironment. Clinically, elevated CBX3⁺GPNMB⁺ CTCs and plasma CXCL12 were significantly associated with BM progression in lung cancer and melanoma. Therapeutically, dual blockade of GPNMB and PD1 enhanced anti-BM efficacy in mice, unveiling GPNMB as a promising target for precision immunotherapy.

PMID:41973996 | DOI:10.1158/2159-8290.CD-25-1663

GA-GS: Generation-Assisted Gaussian Splatting for Static Scene Reconstruction

cs.AI, q-bio.NC updates on arXiv.org

By: Yedong Shen · Shiqi Zhang · Sha Zhang · Yifan Duan · Xinran Zhang · Wenhao Yu · Lu Zhang · Jiajun Deng · Yanyong Zhang

7 April 2026 at 12:00

arXiv:2604.04331v1 Announce Type: cross Abstract: Reconstructing static 3D scene from monocular video with dynamic objects is important for numerous applications such as virtual reality and autonomous driving. Current approaches typically rely on background for static scene reconstruction, limiting the ability to recover regions occluded by dynamic objects. In this paper, we propose GA-GS, a Generation-Assisted Gaussian Splatting method for Static Scene Reconstruction. The key innovation of our work lies in leveraging generation to assist in reconstructing occluded regions. We employ a motion-aware module to segment and remove dynamic regions, and thenuse a diffusion model to inpaint the occluded areas, providing pseudo-ground-truth supervision. To balance contributions from real background and generated region, we introduce a learnable authenticity scalar for each Gaussian primitive, which dynamically modulates opacity during splatting for authenticity-aware rendering and supervision. Since no existing dataset provides ground-truth static scene of video with dynamic objects, we construct a dataset named Trajectory-Match, using a fixed-path robot to record each scene with/without dynamic objects, enabling quantitative evaluation in reconstruction of occluded regions. Extensive experiments on both the DAVIS and our dataset show that GA-GS achieves state-of-the-art performance in static scene reconstruction, especially in challenging scenarios with large-scale, persistent occlusions.

Lightweight liquid neural networks decipher salivary metabolic fingerprinting for high-risk periodontitis screening in diabetes

npj Digital Medicine

By: Yizhou Liu · Ya Zhao · Zhenhe Chen · Qin Liang · Yajuan Lei · Lilei Zhu · Xiaodong Li · Chao Yuan

7 April 2026 at 08:00

npj Digital Medicine, Published online: 07 April 2026; doi:10.1038/s41746-026-02593-7

Lightweight liquid neural networks decipher salivary metabolic fingerprinting for high-risk periodontitis screening in diabetes

AffordTissue: Dense Affordance Prediction for Tool-Action Specific Tissue Interaction

cs.AI, q-bio.NC updates on arXiv.org

By: Aiza Maksutova · Lalithkumar Seenivasan · Hao Ding · Jiru Xu · Chenhao Yu · Chenyan Jing · Yiqing Shen · Mathias Unberath

3 April 2026 at 12:00

arXiv:2604.01371v1 Announce Type: cross Abstract: Surgical action automation has progressed rapidly toward achieving surgeon-like dexterous control, driven primarily by advances in learning from demonstration and vision-language-action models. While these have demonstrated success in table-top experiments, translating them to clinical deployment remains challenging: current methods offer limited predictability on where instruments will interact on tissue surfaces and lack explicit conditioning inputs to enforce tool-action-specific safe interaction regions. Addressing this gap, we introduce AffordTissue, a multimodal framework for predicting tool-action specific tissue affordance regions as dense heatmaps during cholecystectomy. Our approach combines a temporal vision encoder capturing tool motion and tissue dynamics across multiple viewpoints, language conditioning enabling generalization across diverse instrument-action pairs, and a DiT-style decoder for dense affordance prediction. We establish the first tissue affordance benchmark by curating and annotating 15,638 video clips across 103 cholecystectomy procedures, covering six unique tool-action pairs involving four instruments (hook, grasper, scissors, clipper) and their associated tasks: dissection, grasping, clipping, and cutting. Experiments demonstrate substantial improvement over vision-language model baselines (20.6 px ASSD vs. 60.2 px for Molmo-VLM), showing that our task-specific architecture outperforms large-scale foundation models for dense surgical affordance prediction. By predicting tool-action specific tissue affordance regions, AffordTissue provides explicit spatial reasoning for safe surgical automation, potentially unlocking explicit policy guidance toward appropriate tissue regions and early safe stop when instruments deviate outside predicted safe zones.

Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models

cs.AI, q-bio.NC updates on arXiv.org

By: Jiawei Chen · Simin Huang · Jiawei Du · Shuaihang Chen · Yu Tian · Mingjie Wei · Chao Yu · Zhaoxia Yin

3 April 2026 at 12:00

arXiv:2604.01618v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have shown strong performance in robotic manipulation, yet their robustness to physically realizable adversarial attacks remains underexplored. Existing studies reveal vulnerabilities through language perturbations and 2D visual attacks, but these attack surfaces are either less representative of real deployment or limited in physical realism. In contrast, adversarial 3D textures pose a more physically plausible and damaging threat, as they are naturally attached to manipulated objects and are easier to deploy in physical environments. Bringing adversarial 3D textures to VLA systems is nevertheless nontrivial. A central obstacle is that standard 3D simulators do not provide a differentiable optimization path from the VLA objective function back to object appearance, making it difficult to optimize through an end-to-end manner. To address this, we introduce Foreground-Background Decoupling (FBD), which enables differentiable texture optimization through dual-renderer alignment while preserving the original simulation environment. To further ensure that the attack remains effective across long-horizon and diverse viewpoints in the physical world, we propose Trajectory-Aware Adversarial Optimization (TAAO), which prioritizes behaviorally critical frames and stabilizes optimization with a vertex-based parameterization. Built on these designs, we present Tex3D, the first framework for end-to-end optimization of 3D adversarial textures directly within the VLA simulation environment. Experiments in both simulation and real-robot settings show that Tex3D significantly degrades VLA performance across multiple manipulation tasks, achieving task failure rates of up to 96.7\%. Our empirical results expose critical vulnerabilities of VLA systems to physically grounded 3D adversarial attacks and highlight the need for robustness-aware training.

GISTBench: Evaluating LLM User Understanding via Evidence-Based Interest Verification

cs.AI, q-bio.NC updates on arXiv.org

By: Iordanis Fostiropoulos · Muhammad Rafay Azhar · Abdalaziz Sawwan · Boyu Fang · Yuchen Liu · Jiayi Liu · Hanchao Yu · Qi Guo · Jianyu Wang · Fei Liu · Xiangjun Fan

1 April 2026 at 12:00

arXiv:2603.29112v1 Announce Type: new Abstract: We introduce GISTBench, a benchmark for evaluating Large Language Models' (LLMs) ability to understand users from their interaction histories in recommendation systems. Unlike traditional RecSys benchmarks that focus on item prediction accuracy, our benchmark evaluates how well LLMs can extract and verify user interests from engagement data. We propose two novel metric families: Interest Groundedness (IG), decomposed into precision and recall components to separately penalize hallucinated interest categories and reward coverage, and Interest Specificity (IS), which assesses the distinctiveness of verified LLM-predicted user profiles. We release a synthetic dataset constructed on real user interactions on a global short-form video platform. Our dataset contains both implicit and explicit engagement signals and rich textual descriptions. We validate our dataset fidelity against user surveys, and evaluate eight open-weight LLMs spanning 7B to 120B parameters. Our findings reveal performance bottlenecks in current LLMs, particularly their limited ability to accurately count and attribute engagement signals across heterogeneous interaction types.

SAW: Toward a Surgical Action World Model via Controllable and Scalable Video Generation

cs.AI, q-bio.NC updates on arXiv.org

By: Sampath Rapuri · Lalithkumar Seenivasan · Dominik Schneider · Roger Soberanis-Mukul · Yufan He · Hao Ding · Jiru Xu · Chenhao Yu · Chenyan Jing · Pengfei Guo · Daguang Xu · Mathias Unberath

16 March 2026 at 12:00

arXiv:2603.13024v1 Announce Type: cross Abstract: A surgical world model capable of generating realistic surgical action videos with precise control over tool-tissue interactions can address fundamental challenges in surgical AI and simulation -- from data scarcity and rare event synthesis to bridging the sim-to-real gap for surgical automation. However, current video generation methods, the very core of such surgical world models, require expensive annotations or complex structured intermediates as conditioning signals at inference, limiting their scalability. Other approaches exhibit limited temporal consistency across complex laparoscopic scenes and do not possess sufficient realism. We propose Surgical Action World (SAW) -- a step toward surgical action world modeling through video diffusion conditioned on four lightweight signals: language prompts encoding tool-action context, a reference surgical scene, tissue affordance mask, and 2D tool-tip trajectories. We design a conditional video diffusion approach that reformulates video-to-video diffusion into trajectory-conditioned surgical action synthesis. The backbone diffusion model is fine-tuned on a custom-curated dataset of 12,044 laparoscopic clips with lightweight spatiotemporal conditioning signals, leveraging a depth consistency loss to enforce geometric plausibility without requiring depth at inference. SAW achieves state-of-the-art temporal consistency (CD-FVD: 199.19 vs. 546.82) and strong visual quality on held-out test data. Furthermore, we demonstrate its downstream utility for (a) surgical AI, where augmenting rare actions with SAW-generated videos improves action recognition (clipping F1-score: 20.93% to 43.14%; cutting: 0.00% to 8.33%) on real test data, and (b) surgical simulation, where rendering tool-tissue interaction videos from simulator-derived trajectory points toward a visually faithful simulation engine.

Accelerating Video Generation Inference with Sequential-Parallel 3D Positional Encoding Using a Global Time Index

cs.AI, q-bio.NC updates on arXiv.org

By: Chao Yuan · Pan Li

10 March 2026 at 12:00

arXiv:2603.06664v1 Announce Type: cross Abstract: Diffusion Transformer (DiT)-based video generation models inherently suffer from bottlenecks in long video synthesis and real-time inference, which can be attributed to the use of full spatiotemporal attention. Specifically, this mechanism leads to explosive O(N^2) memory consumption and high first-frame latency. To address these issues, we implement system-level inference optimizations for a causal autoregressive video generation pipeline. We adapt the Self-Forcing causal autoregressive framework to sequence parallel inference and implement a sequence-parallel variant of the causal rotary position embedding which we refer to as Causal-RoPE SP. This adaptation enables localized computation and reduces cross-rank communication in sequence parallel execution. In addition, computation and communication pipelines are optimized through operator fusion and RoPE precomputation. Experiments conducted on an eight GPU A800 cluster show that the optimized system achieves comparable generation quality, sub-second first-frame latency, and near real-time inference speed. For generating five second 480P videos, a 1.58x speedup is achieved, thereby providing effective support for real-time interactive applications.

Survey of Computerized Adaptive Testing: A Machine Learning Perspective

cs.AI, q-bio.NC updates on arXiv.org

By: Yan Zhuang · Qi Liu · Haoyang Bi · Zhenya Huang · Weizhe Huang · Jiatong Li · Junhao Yu · Zirui Liu · Zirui Hu · Yuting Hong · Zachary A. Pardos · Haiping Ma · Mengxiao Zhu · Shijin Wang · Enhong Chen

10 March 2026 at 12:00

arXiv:2404.00712v3 Announce Type: replace-cross Abstract: Computerized Adaptive Testing (CAT) offers an efficient and personalized method for assessing examinee proficiency by dynamically adjusting test questions based on individual performance. Compared to traditional, non-personalized testing methods, CAT requires fewer questions and provides more accurate assessments. As a result, CAT has been widely adopted across various fields, including education, healthcare, sports, sociology, and the evaluation of AI models. While traditional methods rely on psychometrics and statistics, the increasing complexity of large-scale testing has spurred the integration of machine learning techniques. This paper aims to provide a machine learning-focused survey on CAT, presenting a fresh perspective on this adaptive testing paradigm. We delve into measurement models, question selection algorithm, bank construction, and test control within CAT, exploring how machine learning can optimize these components. Through an analysis of current methods, strengths, limitations, and challenges, we strive to develop robust, fair, and efficient CAT systems. By bridging psychometric-driven CAT research with machine learning, this survey advocates for a more inclusive and interdisciplinary approach to the future of adaptive testing.

Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents

cs.AI, q-bio.NC updates on arXiv.org

By: Yueqi Song · Ketan Ramaneti · Zaid Sheikh · Ziru Chen · Boyu Gou · Tianbao Xie · Yiheng Xu · Danyang Zhang · Apurva Gandhi · Fan Yang · Joseph Liu · Tianyue Ou · Zhihao Yuan · Frank Xu · Shuyan Zhou · Xingyao Wang · Xiang Yue · Tao Yu · Huan Sun · Yu Su · Graham Neubig

5 March 2026 at 13:00

arXiv:2510.24702v2 Announce Type: replace-cross Abstract: Public research results on large-scale supervised finetuning of AI agents remain relatively rare, since the collection of agent training data presents unique challenges. In this work, we argue that the bottleneck is not a lack of underlying data sources, but that a large variety of data is fragmented across heterogeneous formats, tools, and interfaces. To this end, we introduce the agent data protocol (ADP), a light-weight representation language that serves as an "interlingua" between agent datasets in diverse formats and unified agent training pipelines downstream. The design of ADP is expressive enough to capture a large variety of tasks, including API/tool use, browsing, coding, software engineering, and general agentic workflows, while remaining simple to parse and train on without engineering at a per-dataset level. In experiments, we unified a broad collection of 13 existing agent training datasets into ADP format, and converted the standardized ADP data into training-ready formats for multiple agent frameworks. We performed SFT on these data, and demonstrated an average performance gain of ~20% over corresponding base models, and delivers state-of-the-art or near-SOTA performance on standard coding, browsing, tool use, and research benchmarks, without domain-specific tuning. All code and data are released publicly, in the hope that ADP could help lower the barrier to standardized, scalable, and reproducible agent training.

Boolean Satisfiability via Imitation Learning

cs.AI, q-bio.NC updates on arXiv.org

By: Zewei Zhang · Huan Liu · Yuanhao Yu · Jun Chen · Xiangyu Xu

24 February 2026 at 13:00

arXiv:2509.25411v2 Announce Type: replace Abstract: We propose ImitSAT, a branching policy for conflict-driven clause learning (CDCL) solvers based on imitation learning for the Boolean satisfiability problem (SAT). Unlike previous methods that predict instance-level signals to improve CDCL branching indirectly, or rely on reinforcement learning and insufficient CDCL information to enhance branching, ImitSAT learns from expert KeyTrace that collapses a full run into the sequence of surviving decisions. Replaying a KeyTrace on the same instance is nearly conflict-free, providing dense decision-level supervision and directly reducing propagations -- the dominant contributor to wall-clock time. This prefix-conditioned supervision enables ImitSAT to reproduce high-quality branches without exploration, yielding faster convergence, stable training, and seamless integration into CDCL. Extensive experiments demonstrate that ImitSAT reduces propagation counts and runtime, outperforming state-of-the-art learned approaches. We released the source code and trained model at https://github.com/zewei-Zhang/ImitSAT

WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL

cs.AI, q-bio.NC updates on arXiv.org

By: Zhennan Jiang · Shangqing Zhou · Yutong Jiang · Zefang Huang · Mingjie Wei · Yuhui Chen · Tianxing Zhou · Zhen Guo · Hao Lin · Quanlu Zhang · Yu Wang · Haoran Li · Chao Yu · Dongbin Zhao

17 February 2026 at 13:00

arXiv:2602.13977v1 Announce Type: cross Abstract: Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision-Language-Action (VLA) models, but its requirement for massive real-world interaction prevents direct deployment on physical robots. Recent work attempts to use learned world models as simulators for policy optimization, yet closed-loop imagined rollouts inevitably suffer from hallucination and long-horizon error accumulation. Such errors do not merely degrade visual fidelity; they corrupt the optimization signal, encouraging policies to exploit model inaccuracies rather than genuine task progress. We propose WoVR, a reliable world-model-based reinforcement learning framework for post-training VLA policies. Instead of assuming a faithful world model, WoVR explicitly regulates how RL interacts with imperfect imagined dynamics. It improves rollout stability through a controllable action-conditioned video world model, reshapes imagined interaction to reduce effective error depth via Keyframe-Initialized Rollouts, and maintains policy-simulator alignment through World Model-Policy co-evolution. Extensive experiments on LIBERO benchmarks and real-world robotic manipulation demonstrate that WoVR enables stable long-horizon imagined rollouts and effective policy optimization, improving average LIBERO success from 39.95% to 69.2% (+29.3 points) and real-robot success from 61.7% to 91.7% (+30.0 points). These results show that learned world models can serve as practical simulators for reinforcement learning when hallucination is explicitly controlled.

Automated Proof Generation for Rust Code via Self-Evolution

cs.AI, q-bio.NC updates on arXiv.org

By: Tianyu Chen · Shuai Lu · Shan Lu · Yeyun Gong · Chenyuan Yang · Xuheng Li · Md Rakib Hossain Misu · Hao Yu · Nan Duan · Peng Cheng · Fan Yang · Shuvendu K Lahiri · Tao Xie · Lidong Zhou

17 February 2026 at 13:00

arXiv:2410.15756v3 Announce Type: replace-cross Abstract: Ensuring correctness is crucial for code generation. Formal verification offers a definitive assurance of correctness, but demands substantial human effort in proof construction and hence raises a pressing need for automation. The primary obstacle lies in the severe lack of data-there is much fewer proofs than code snippets for Large Language Models (LLMs) to train upon. In this paper, we introduce SAFE, a framework that overcomes the lack of human-written proofs to enable automated proof generation of Rust code. SAFE establishes a self-evolving cycle where data synthesis and fine-tuning collaborate to enhance the model capability, leveraging the definitive power of a symbolic verifier in telling correct proofs from incorrect ones. SAFE also re-purposes the large number of synthesized incorrect proofs to train the self-debugging capability of the fine-tuned models, empowering them to fix incorrect proofs based on the verifier's feedback. SAFE demonstrates superior efficiency and precision compared to GPT-4o. Through tens of thousands of synthesized proofs and the self-debugging mechanism, we improve the capability of open-source models, initially unacquainted with formal verification, to automatically write proofs for Rust code. This advancement leads to a significant improvement in performance, achieving a 52.52% accuracy rate in a benchmark crafted by human experts, a significant leap over GPT-4o's performance of 14.39%.

C^2ROPE: Causal Continuous Rotary Positional Encoding for 3D Large Multimodal-Models Reasoning

cs.AI, q-bio.NC updates on arXiv.org

By: Guanting Ye · Qiyan Zhao · Wenhao Yu · Xiaofeng Zhang · Jianmin Ji · Yanyong Zhang · Ka-Veng Yuen

17 February 2026 at 13:00

arXiv:2602.10551v2 Announce Type: replace-cross Abstract: Recent advances in 3D Large Multimodal Models (LMMs) built on Large Language Models (LLMs) have established the alignment of 3D visual features with LLM representations as the dominant paradigm. However, the inherited Rotary Position Embedding (RoPE) introduces limitations for multimodal processing. Specifically, applying 1D temporal positional indices disrupts the continuity of visual features along the column dimension, resulting in spatial locality loss. Moreover, RoPE follows the prior that temporally closer image tokens are more causally related, leading to long-term decay in attention allocation and causing the model to progressively neglect earlier visual tokens as the sequence length increases. To address these issues, we propose C^2RoPE, an improved RoPE that explicitly models local spatial Continuity and spatial Causal relationships for visual processing. C^2RoPE introduces a spatio-temporal continuous positional embedding mechanism for visual tokens. It first integrates 1D temporal positions with Cartesian-based spatial coordinates to construct a triplet hybrid positional index, and then employs a frequency allocation strategy to encode spatio-temporal positional information across the three index components. Additionally, we introduce Chebyshev Causal Masking, which determines causal dependencies by computing the Chebyshev distance of image tokens in 2D space. Evaluation results across various benchmarks, including 3D scene reasoning and 3D visual question answering, demonstrate C^2RoPE's effectiveness. The code is be available at https://github.com/ErikZ719/C2RoPE.

Reading view