Artificial Intelligence
AssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture Assembly
Zhiyuan Qi, Jierui Li, Yifan Shen et al. (+2 more)
Multimodal large
language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial
reasoning integrated with physical environment remains difficult. Furniture assembly requires not only recovering step-level operations from diagrammatic manuals, but also translating semantic attachment relations into 6D pose updates that enable parts to physically interact with the environment and previously assembled components. To study this problem, we propose AssemState, a zero-shot framework for manual and physical-state-guided furniture assembly. It firstly employs anchor-guided boundary assembly states to decompose manual pages into single-part operations and recover an assembly-tree. Then, it uses iterative after-state feedback refinement to guide successive (SE(3)) updates and corrections, and validates their physical plausibility through simulation-based release tests. Experiments show that compared with the strongest prior baseline, AssemState improves F1 from 38.58% to 62.80% and Tree Exact Match from 28.24% to 53.92% for assembly-tree recovery. On 243 independently evaluated part-level operations, our proposed iterative refinement improves judge-accepted operations from 0 to 5.3% and reduces mean Chamfer distance from 5.4111 to 1.7744. However, visually plausible candidate poses may still suffer from collision, floating, mirror-orientation errors, incomplete seating, and wrong-side attachment. These results show that AssemState improves operation-structure recovery and selected local pose metrics, while MLLMs remain limited for spatial relationship
reasoning.
Read the full abstract ▾
All authors Zhiyuan Qi, Jierui Li, Yifan Shen, Cheng Qian, Jiateng Liu
Artificial Intelligence
EMHO: EMbodied Agent Harness Optimization via Experience Traces
Hyun Jung Lee, Jungtaek Kim, Jongwon Jeong et al. (+3 more)
Improving embodied
agents often focuses on optimizing the underlying model through training, while the surrounding
agent harness that controls planning, context, and tool use is typically engineered. We ask whether this harness can instead improve itself directly from experience traces under sparse environmental feedback. We propose EMbodied
Agent Harness Optimization (EMHO), a self-evolving framework that keeps the embodied model frozen and iteratively revises its harness by analyzing execution trajectories and prior harness history. EMHO optimizes beyond skills or recovery
prompts, modifying how the
agent monitors progress, uses
vision tools, grounds observations, and responds to failures. To support multiple subtasks with a single harness, we introduce EMHO-Merge, which addresses trade-offs in jointly optimizing a single shared harness across subtasks by using episode-level gains and losses to guide evidence-supported refinement of when and how revised behaviors are applied. We evaluate EMHO on EmbodiedBench across navigation and manipulation tasks, and EMHO consistently improves task success for both Qwen 9B and 27B models. Qualitative analysis shows that EMHO goes beyond recovering from failures and unproductive actions to reshape how the embodied
agent interprets and interacts with its environment.
Read the full abstract ▾
All authors Hyun Jung Lee, Jungtaek Kim, Jongwon Jeong, Tae-Eui Kam, Donghyun Kim, Yong Jae Lee
Artificial Intelligence · Cross-listed from cs.DC
NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale
Songlin Jiang, Zhiyu Li, Terry Kong et al. (+5 more)
Agentic reinforcement learning (RL) disaggregates training from rollout, so each policy update must reach the rollout clusters before the next batch. Transferring a full 1T checkpoint for such weight synchronization (refit) takes 87.5 min between two AWS regions. Measurements of BF16 training show that about 1% of weights change their stored values per step. Recent systems exploit this sparsity but fall short on placement, exactness, or efficiency: they reimplement placement rules, assemble full tensors, rebuild values arithmetically, or use a cross-cluster collective, and none fully recovers from mid-refit failures. We present NeMo-DCR (Delta-Compressed Refit), which sends only changes yet is bit-exact: receivers obtain the same parameter and buffer bits as a dense refit. For placement, fixed affine mappings project changes from training shards into the checkpoint's canonical coordinates, residual conversion covers the other changes, and the serving runtime's native loader places all changes in receiver storage. For exactness, compressible XOR masks carry affine changes whose projection and loader preserve stored bits, and overwrites carry the others. Receivers apply both in place, retries overwrite partial writes, and a joint commit binds the policy to the baseline for the next delta. For efficiency, object storage or a relay tree streams payloads during delta construction, without a cross-cluster collective. Even at 3% and 5% change rates, NeMo-DCR refits of 30B-1T models are 12-40$\times$ faster than a transport-only full-checkpoint reference. A 1T relay-tree refit at 3% takes 150 s instead of 87.5 min, making refits practical for cross-cluster agentic RL at trillion-parameter scale.
Read the full abstract ▾
All authors Songlin Jiang, Zhiyu Li, Terry Kong, Yu Yao, Youngeun Kwon, Bernard Nguyen, Ashwath Aithal, Mario Di Francesco
Artificial Intelligence · Cross-listed from cs.CL
Knowing When Not to Answer: Cross-Domain and Multi-Turn Generalization of Latent Underspecification Signals
Jerzy Kamiński, Ilya Galyukshev, Artem Kuznetsov et al. (+6 more)
Large
language models routinely answer questions that cannot be answered from the information given, and in dialogue they answer before enough has been said. Unanswerability is linearly decodable from hidden states, but it is unclear which of its forms share a representation and whether the signal is useful in dialogue. We contribute a turn-labeled multi-turn
benchmark (423 conversations, 1,661 labeled turn-states) and an evaluation harness with a simulated user who answers clarifying questions, and use them with six
datasets and six open-weight LLMs to test how far probes for unanswerability carry. Probes transfer robustly between
datasets that share a ground of unanswerability: missing information in math (AUROC 0.77-0.97) and in a passage (SQuAD 2.0<->MuSiQue, 0.77-0.90). Probes for epistemic "known-unknowns" transfer poorly to math, but this separation weakens under lexical controls and changes with layer and coordinate system, so it remains unresolved. Single-turn probes fail zero-shot to detect when a conversation becomes answerable; in-structure probes recover it, but no better than a bag-of-words classifier. A gate on the calibrated probe, with no model fine-tuning, fires on underspecified turns far more precisely than chance, and its end-task success comes within 0.08 of a gate given the true labels. Yet across four models it does not reliably beat vanilla generation or prompted consolidation. The remaining gap lies mostly in how models use a clarification, not in detection.
Read the full abstract ▾
All authors Jerzy Kamiński, Ilya Galyukshev, Artem Kuznetsov, Danil Fedorov, Kirill Redko, Sergey Chuprin, Aidar Shumbalov, Stanislav Chumakov, Anna Kalyuzhnaya
Artificial Intelligence · Cross-listed from cs.SE
Learning from Failures: A Failure-Driven Prompt Refinement for LLM-Based Vulnerability Analysis
Mandana Ghadamian and David Mohaisen
Large
Language Models have emerged as promising tools for software vulnerability analysis, but their effectiveness depends heavily on
prompt design. Existing research primarily compares prompting strategies using aggregate performance metrics, providing limited insight into why models fail or how
prompts can be improved systematically. We propose Failure-Driven
Prompt Refinement (FDPR), a methodology that analyzes recurring model failures to guide evidence-based
prompt refinement. Using the Damn Vulnerable Java Application (DVJA), we identify recurring failure modes, including false positives, false negatives, unsupported
reasoning, and CWE misclassification, and translate them into targeted
prompt refinements. We then evaluate the resulting
prompt on the Juliet Test Suite and perform cross-model validation to assess generalizability. The results show that failure-driven refinement improves the reliability of LLM-based vulnerability analysis while yielding reusable
prompt design principles. More broadly, this work demonstrates that recurring model failures provide a principled foundation for
prompt engineering, enabling the systematic development of more reliable LLM-based vulnerability analysis systems.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
GeoPID: Decomposing and Steering Visual Information in Vision-Language Models
Seulgi Kim, Zhixiong Zhang, Xinwei Zhang et al. (+2 more)
While recent
vision-
language models (VLMs) have shown outstanding performance across diverse applications, they tend to under-use visual information and over-rely on textual context. In this work, we propose GeoPID, a training-free framework that analyzes
multimodal information within VLMs from a
geometric perspective. GeoPID decomposes information into Redundant, Modality-Unique, and Synergistic components through the
geometric relationships between visual and textual representation subspaces. Through an extensive analysis across 22 VLMs and 14
benchmarks, we confirm that correct predictions exhibit stronger
vision-unique components when questions strongly require visual grounding. Building on this
geometric analysis, we introduce a targeted intervention technique that selectively amplifies visual representations along the
vision-unique subspace during inference. As a result, visual grounding capabilities were enhanced without any additional model parameter updates, achieving an average relative accuracy gain of 7.63%.
Read the full abstract ▾
All authors Seulgi Kim, Zhixiong Zhang, Xinwei Zhang, Jie Ling, Ronn Shaw
Artificial Intelligence · Cross-listed from cs.LG
Atom-JEPA: Joint-Embedding Predictive Architecture for 3D Atomistic Systems
Kasper Helverskov Petersen, Rasmus Hannibal Tirsgaard, François R J Cornet et al. (+2 more)
Large-scale self-supervised pretraining has reshaped modern machine learning, substantially advancing the ability of
language and
vision models to generalize across downstream tasks. While deep learning has driven considerable progress in modeling atomistic systems in recent years, self-supervised pretraining in this domain has not yet achieved comparable downstream generalization. To address this, we introduce Atom-JEPA, a self-supervised pretraining framework that learns latent representations from unlabeled 3D structures through complementary atom-level and substructure-level objectives inspired by joint-
embedding predictive architectures. We pretrain Atom-JEPA on large-scale molecular and crystalline
datasets and evaluate its transfer performance by fine-tuning on a diverse set of downstream property prediction tasks. Atom-JEPA achieves state-of-the-art performance on molecular ADMET and
quantum-chemical property prediction tasks, and is highly competitive in predicting the physical properties of crystalline materials. These results demonstrate the potential of latent-space predictive pretraining to support broad downstream generalization from structural data alone. Code and pretrained model checkpoints are publicly available at https://github.com/khelverskovp/atom-jepa
Read the full abstract ▾
All authors Kasper Helverskov Petersen, Rasmus Hannibal Tirsgaard, François R J Cornet, Mikkel Jordahn, Mikkel N. Schmidt
Artificial Intelligence · Cross-listed from cs.CL
Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering
Yang Hong, Yajun Yang, Xin Wang et al. (+2 more)
Large
language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suffer from
hallucinations on knowledge-intensive tasks. Knowledge graphs (KGs) provide LLMs with structured, interpretable, and updatable factual grounding, making them a promising external knowledge source for reliable
reasoning. However, existing LLM-guided graph
reasoning methods typically rely on hop-wise greedy or beam-style
pruning during evidence
retrieval. Such local decision processes are inherently myopic: evidence that appears weak near the source may become crucial only after deeper graph context is explored, causing answer-critical branches to be discarded prematurely and making the
reasoning chain difficult to recover. To address this limitation, we propose Foresight-over-Graph (FoG), a foresight-aware evidence
retrieval framework for knowledge base question answering (KBQA). FoG iteratively constructs a question-relevant evidence subgraph and uses far-to-near feedback to guide path exploration, and maintains a compact
memory subgraph to support continued exploration. Extensive experiments on widely used KBQA
benchmarks demonstrate that FoG achieves state-of-the-art performance, with a particularly large improvement of 16.58% in Hit on CWQ, while also reducing LLM calls and
token usage. Our code is available at https://github.com/yhong7/FoG .
Read the full abstract ▾
All authors Yang Hong, Yajun Yang, Xin Wang, Liping Jing, Qinghua Hu
Artificial Intelligence · Cross-listed from cs.LG
Accelerating the Development of PLGA In Situ Forming Depots Through AI-Driven Multi-Objective Optimization
Pauric Bannigan, Siddarth Chandrasekaran, Brigitte A. G. Lamers et al. (+6 more)
Developing long-acting injectable formulations requires the simultaneous optimization of drug loading, release kinetics, viscosity, injectability, stability and other objectives. To navigate this multidimensional space, Corbion and Intrepid combined Corbion's diverse PURASORB bioresorbable
polymer library with Intrepid Labs' proprietary AI
algorithm (ANDROMEDA 1) to develop in situ forming depots for a therapeutic peptide. Over approximately 15 weeks, 181 unique formulations spanning drug loadings of 6-12% w/w were prepared and characterized through broad design-space mapping and targeted multi-objective optimization. Four lead candidate formulations were identified at 6%, 9%, and 12% w/w drug loading. Each met the predefined viscosity and injectability criteria while providing distinct 30-day in vitro release profiles. The study evaluated
polymers spanning a broad range of molecular weights, including commercially available PURASORB grades and new
polymers under development by Corbion to expand its
polymer toolbox. ANDROMEDA 1 identified that
polymers with intermediate molecular weights provided a favorable balance between sustained release and solution viscosity. Together, these findings demonstrate how integrated
polymer expertise and AI-driven optimization can rapidly identify differentiated formulation candidates, focus the development space, and establish a strong data-driven foundation for further optimization and in vivo evaluation.
Read the full abstract ▾
All authors Pauric Bannigan, Siddarth Chandrasekaran, Brigitte A. G. Lamers, Inge Hermsen, Gary Tom, Riley J. Hickman, Bahar Yeniad, Morgan Fox, Christine Allen
Artificial Intelligence
Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations
Toby D. Pilditch, Konstantinos Voudouris, Alexandra Abbas et al. (+1 more)
Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions from complex multi-
agent networks. The observability envelop-the range of what evaluators can reliably infer about an
agent's behaviours-is therefore narrowing.
Language model assistants can help classify and interpret
agent behaviour but also afford human evaluators significant analytical degrees of freedom, threatening the reproducibility and auditability of
language-model-based transcript analysis. Transect is an open source package built on Inspect Scout to help evaluators understand how a long
agent run unfolded, identify behaviour worth investigating, and check interpretations against the transcript. Users specify task context and behavioural vocabulary in a reusable evaluation-family configuration, with judge models and analysis settings supplied separately. Transect's navigable reports align recorded events,
token use, sub-
agent activity, and model-generated behavioural labels on a common turn-based timeline. Reviewers can quickly grasp a run's narrative, trace any label or event to its source turns, and export the underlying data tables for cross-run analysis. We demonstrate the workflow on an AI R&D evaluation that generated almost 13 million
tokens, dividing the
agents' work into behavioural phases aligned with research-skill classifications, sub-
agent delegations and interactions, and
token use. The combined view shows a focus on operational work and manuscript production, with little evidence of a sustained hypothesis generation stage-arguably a necessary component for high-quality scientific outputs. Transect's flexible, customisable transcript-analysis pipeline will enable evaluators to keep pace with longer, more complex, more frequent AI evaluations while supporting scientific rigour, transparency, and reproducibility.
Read the full abstract ▾
All authors Toby D. Pilditch, Konstantinos Voudouris, Alexandra Abbas, Cozmin Ududec
Artificial Intelligence
Explainable Failure Prediction and Prevention in Maritime
Dionisis Kalogeropoulos, Georgia Sovatzidi, Panagiotis G. Kalozoumis et al. (+1 more)
Maritime systems operate in highly dynamic environments where unexpected equipment failures can compromise safety, reliability, and operational efficiency. Recent advances in artificial intelligence (AI), machine learning, digital twins, and predictive maintenance enable proactive failure prediction and prevention. However, ensuring trustworthy and explainable decision-making remains a major challenge in safety-critical maritime applications. This chapter reviews key AI technologies required for explainable failure prediction and prevention in maritime systems and presents a conceptual architecture capable of supporting autonomous or human-in-the-loop corrective actions. This architecture integrates data acquisition, time-series forecasting, anomaly detection, risk assessment, decision-making, and explainable AI into a closed-loop framework. With reference to the architectural components, a review and discussion of relevant maritime studies is performed, outlining their methods, advantages, and limitations. Furthermore, it highlights current challenges, including uncertainty and robustness, model generalization, explainability, limited availability of maritime
datasets, and operational deployment, and identifies future research directions toward trustworthy AI-assisted maritime decision-making.
Read the full abstract ▾
All authors Dionisis Kalogeropoulos, Georgia Sovatzidi, Panagiotis G. Kalozoumis, Dimitris K. Iakovidis
Artificial Intelligence · Cross-listed from cs.CV
Test-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned Recalibration
Hyeongheon Cha, Young D. Kwon and Sung-Ju Lee
Post-training quantization is a standard route to fitting
vision transformers (ViTs) into edge compute and
memory budgets, yet quantized models become especially brittle under distribution shift. Test-time adaptation (TTA) addresses such shifts without labels, but most existing approaches are poorly aligned with the constraints of quantized inference. Prevailing TTA methods recover accuracy through backpropagation, while backprop-free methods often still incur overhead from extra forward passes or parameter updates, and lightweight feature- or logit-level methods recover only part of the loss. Across these approaches, a quantization-specific failure mode that amplifies the drop is not directly targeted: under shift, activations occupy frozen quantizers' calibrated ranges differently, distorting their code distribution. We propose Quantizer-Aligned Recalibration (QuAR), a single-pass TTA method tailored to quantized ViTs that neither backpropagates nor updates any model parameters. QuAR recalibrates activations at the input to a frozen quantizer, mapping the test stream's running per-channel statistics back toward the source calibration. On ImageNet-C with ViT-B, QuAR achieves the highest mean accuracy among state-of-the-art backprop-free TTA methods at 3-, 4-, 6- and 8-bit weight/activation precision, outperforming the strongest baseline by 2.28 points at 8 bits and 4.00 at 3 bits, with 46% lower latency and a
memory overhead of only 0.17 MB (0.01% of peak inference
memory). Analysis and diagnostics trace the gain to a reduced per-channel mismatch at these quantizers, which restores the code distribution the baselines leave unchanged or distort further. A single fixed configuration remains ahead across continual streams, non-i.i.d. label shift, seven out-of-distribution suites, and three other backbones.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Sensor Geometry as a Flow-Matching Prior for Multi-Channel Brain Signals
Jaedong Hwang
Flow-matching models start from an isotropic Gaussian source, the standard choice when the correlation structure of the data is unknown in advance. For multi-channel
brain recordings, however, part of this structure is known in advance. Electrodes sit at fixed positions on the head, and volume conduction through the skull and scalp makes nearby electrodes co-vary in a way that is shared across subjects. Existing
EEG generative models nonetheless leave the network to learn this from scratch. We put this structure into the source instead. From the sensor coordinates alone, we build a k-nearest-neighbor graph and take a graph-Matérn function of its
Laplacian as the source covariance, so the flow starts from spatially coherent patterns rather than channel-independent noise. The change adds no learned parameters, works with any coupling and any drift network, and uses the same three hyperparameters on every
dataset. Across eight
EEG datasets and four flow-matching methods, the graph-Matérn source lowers the spectral discrepancy between generated and real signals in the five clinical bands (PSD-KL) on most
datasets. PSD-KL falls by 12% to 17% in
geometric mean over
datasets depending on the method and by up to 40% on PhysioNet-MI, the densest montage. We show that the improvement stems from the spatial eigenvectors of the local graph of sensor positions, since randomizing the eigenvectors while preserving the
eigenvalue spectrum eliminates the gain. Furthermore, a prior fitted directly to the empirical data covariance performs worse than isotropic noise. The same construction applies unchanged to MEG, intracranial
EEG with patient-specific grids, and a traffic-sensor network, lowering PSD-KL for every method on each. https://jd730.github.io/projects/GraphPrior
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
How Much Planning Is Enough? Reducing Search and Computation in World-Model Planning
Changbai Li, Sirui Li, Yichen Yang et al. (+4 more)
Visual world models enable goal-directed control through decision-time action search, but their deployment efficiency is often limited by conservatively large planning budgets. We show that competitive task performance can be achieved without agreement with the Full-budget action, that sufficient budgets vary across model–task pairs, and that iterative planners repeatedly encode solve-invariant context. To address these inefficiencies, we propose {SufficientPlan}, a simple deployment framework that requires no modification to pretrained world models or planner updates. Its {Paired Sequential Budget Certification (PSBC)} component uses paired closed-loop evidence to search for and certify a reduced model–task-specific budget within a predefined Full-performance tolerance. Its {Static-Context Reuse (SCR)} component caches observation and goal representations across search iterations while preserving candidate-dependent planning and selected actions. Experiments across multiple world-model backbones and visual-control tasks show that SufficientPlan substantially reduces search budgets and planning latency while maintaining competitive control performance.
Read the full abstract ▾
All authors Changbai Li, Sirui Li, Yichen Yang, Tongfei Chen, Zichao Feng, Shuwei Shao, Huobin Tan
Artificial Intelligence · Cross-listed from cs.CV
Transferable Spatial Temporal Coherence Adversarial Attack on Black-Box Vision Language Models for Autonomous Driving
Heyam Bin Jahlan Areej Alhothali Abeer Alhothali
The rapid integration of
Vision Language Models (VLMs) into sensitive systems introduces critical safety vulnerabilities that remain unexplored in exist studies. While
adversarial attack robustness has been extensively studied for image-based models, the susceptibility of VLMs to temporally-aware
adversarial attacks against
video in driving context poses a distinct and under examined threat. In this paper, we introduce novel
adversarial attack against
video targeting VLM models used for autonomous driving scenes named Spatial Temporal Coherence
Adversarial Attack (STCA). Our attack comprise from three stages: modalities expansion, Spatial attack, and STCA attack. In modalities expansion, we propose caption-guided frame selection method in order to ensure that
adversarial perturbation target the most semantically significant frames. Secondly.In spatial attack, we craft effective perturbation and preserve high similarity. Then the perturbed
video generated fed into STCA stage that disrupt cross-frame temporal coherence using motion guided mask. Our method operate under black box threat model against victim target VLMs, relying solely on transferability from white-box surrogate model.We conduct our experiments on the BDD100K and nuScenes autonomous driving
datasets across three VLM models:
Video LLaVA-7B, Qwen2.5-VL-7B, and Dolphin. Experimental results demonstrate spatial attack achieves an ASR with high SSIM. Our finding reveal that existing
video language model, remain highly susceptible to
adversarial attack in autonomous driving scenarios, underscoring the urgent need for robust defense for VLM models.
Read the full abstract ▾
Artificial Intelligence
MoF: Preference-Aware Mixture Modeling for Black-Box LLM Personalization
Hun Park
Proprietary Large
Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet aligning their outputs with diverse user preferences remains challenging. Existing personalization approaches for black-box LLMs often rely on user-specific scoring heads, causing the number of personalized parameters to grow linearly with the number of users and requiring additional adaptation for unseen users. To address these limitations, we propose Mixture-of-Facets (MoF), a scalable personalization framework for black-box LLMs that models user preferences as compositions of shared latent preference facets rather than dedicated user-specific parameters. MoF performs personalization through history-conditioned routing over shared facet heads, enabling personalization for users unseen during training without additional parameter updates. Across diverse personalization tasks, MoF delivers stronger personalization performance while maintaining a more scalable and parameter-efficient design than prior approaches. Additional analysis indicates strong generalization to unseen users.
Read the full abstract ▾
Artificial Intelligence
An AI-Assisted Formalization of the Poincaré Conjecture
Zhiyuan Zhang, Axel Delaval, Leheng Chen et al. (+6 more)
We present an AI-assisted Lean 4 formalization of the Poincaré
conjecture. The project began with limited reusable formal infrastructure for the
geometric analysis behind the proof. To organize this work, we combined a proof blueprint prepared by mathematicians with explicit milestone statements. These milestones enabled parallel
agent work and gave mathematicians clear points to locate blockers and provide effective mathematical guidance. Our analysis identifies the human interventions and organizational choices behind this workflow. The project provides a starting point toward reusable infrastructure for future formalization projects; such infrastructure, once developed, could eventually reduce the cost of verifying mathematical results in
geometric analysis.
Read the full abstract ▾
All authors Zhiyuan Zhang, Axel Delaval, Leheng Chen, Jinxuan Chen, Jie Xu, Yuxuan Liao, Jiedong Jiang, Chunlei Liu, Bin Dong
Artificial Intelligence
MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation
Xilin Dang, Weilin Ruan, Xue Yang et al. (+4 more)
Large
language models (LLMs) have shown promise in medical question answering and clinical
reasoning, yet their improvement remains constrained by static parametric knowledge and costly expert supervision. Self-evolving
agents offer a promising alternative by enabling models to improve through iterative task generation and problem-solving. However, most existing self-evolving methods are designed for easily verifiable domains such as mathematics and coding, where solutions can be checked by exact answers or executable programs. Medical
reasoning is fundamentally different: it is open-ended, knowledge-intensive, and often only partially verifiable. We present MedZERO, a self-evolving framework for open-ended medical
reasoning. MedZERO couples an Examiner that generates frontier medical question-option pairs with a Reasoner that solves them through evidence-grounded multi-turn
reasoning with external knowledge tools. To support reliable, continual improvement, MedZERO adopts controlled knowledge accumulation, which maintains temporary exploratory knowledge and curated persistent knowledge in
reasoning. We evaluate MedZERO on five public medical
reasoning benchmarks using 4B- and 8B-scale base models under open-ended evaluation. Across all settings, MedZERO consistently outperforms the underlying base models and prior self-evolving baselines, achieving up to 13.7 average accuracy-point gains over the next-best self-evolving baseline.
Read the full abstract ▾
All authors Xilin Dang, Weilin Ruan, Xue Yang, Jinghao Wang, Xiaowei Hu, Jinpeng Li, Pheng-Ann Heng
Artificial Intelligence
SCOPE: Certified Theorem Proving with a Language Model as the Policy Planner
Hanchao Zhou and Jialei Li
In proof assistants such as Lean, a generated proof must pass machine compilation checks, so evaluation needs no human scoring. Direct generation fails on multi-step numeric propositions: a proof is valid only if every content integer is correct, so the pass rate is bounded by the k-th power of the per-integer accuracy. Controlled corruption across 2,617 reference proofs confirms this power law. SCOPE (State-Conditioned Operator Planning and Execution) enforces the natural division of labor: the model plans over an operator vocabulary, a symbolic engine executes the numerics, and a compiler renders the proof. On a 218-problem suite it certifies 191/218 (87.6%) with a 135M backbone; the 7B DeepSeek-Prover-V1.5-RL certifies 18/218 at 27.5 times the
tokens and 37.5 times the wall-clock, and DeepSeek-Prover-V2-7B certifies zero on a bidirectional dual suite. Multi-step thinking costs 6.12 discrete decision actions per problem and produces no natural-
language thinking text. Replacing the lagged engine state in the decision frame with the current one lifts the pass rate from 117/218 to 191/218, while up-weighting the chain-end loss hurts. On the public Lean-Workbook library, 2,132 of 3,536 gradeable admissible problems certify (60.29%) with zero regression on the main suite. All readings come from a version-frozen review with independent rechecks and reverse verification. Restricting free generation and keeping decision-time information visible is a more direct route than enlarging the model.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
MARCO: The Radioactive Watermark for Protein Generative Models
Huajie Chen, Xin Guo, Yuchen Shi et al. (+7 more)
Protein Generative Models (PGMs) have revolutionized structural biology by enabling the design of complex 3D
protein structures from sequence data. However, this breakthrough introduces a dual-use challenge, exposing high-value PGMs to economic risks like unauthorized model extraction and biosecurity threats such as biohazard synthesis. To mitigate these threats, we propose MARCO (COnformation waterMARk), the first radioactive watermarking framework specifically tailored for PGMs. MARCO establishes a Dual-Layer defense that simultaneously protects intellectual property and ensures the forensic traceability of potential biosecurity misuses. (i) To preserve efficiency, MARCO iteratively embeds watermarks during
diffusion reverse denoising via an auxiliary encoder-decoder, allowing the original PGM parameters to remain frozen for broad compatibility. (ii) To preserve biophysical fidelity and maximize robustness, we employ specialized loss functions targeting $C_\alpha$-atom pairwise distances and torsion angles ($\psi, \phi$) within an
adversarial training framework integrated with
stochastic attack simulations. (iii) Crucially, MARCO exhibits “radioactivity” where the watermark automatically transfers to the outputs of any pirate models trained on the watermarked data, effectively countering model extraction attacks. Comprehensive experiments demonstrate that MARCO achieves superior fidelity and robustness while successfully validating watermark transferability.
Read the full abstract ▾
All authors Huajie Chen, Xin Guo, Yuchen Shi, Yuchen Zhong, Minhui Xue, Chi Liu, Congcong Zhu, Kun Gao, Minfeng Qi, Tianqing Zhu
Artificial Intelligence
The Standardization Trap: Certifying Joint Label Processing in Tabular Foundation Models
Duong Nguyen, Nicolas Chesneau and Milan Bhan
Linear regression and kernel smoothing offer tractable explanations of in-context learning: in both, the features determine the weight assigned to each context label. However, whether this fixed-weight account describes pretrained tabular foundation models (TFMs) remains unclear. Testing this account using derivatives runs into a standardization trap: public TFM packages standardize the labels before the model sees them, yet ordinary derivatives also reflect behavior outside the set of standardized labels, making a model appear nonlinear even when every prediction it makes agrees with a fixed-weight map. We propose two certificates that depend only on predictions at standardized labels and can reject two distinct explanations: fixed-weight prediction and sums of independent nonlinear label transformations. Across the five public TFMs that we evaluate, our certificates show that changing one context label alters how other labels influence the prediction, a behavior we call joint processing. We further find that joint processing emerges with training and that
attention scores carry most of the measured interaction. Together, these findings motivate TFM explanations that account for how context labels change the influence of individual examples.
Read the full abstract ▾
Artificial Intelligence
CoDe-LoRA: Mitigating the Orthogonality Dilemma in Continual Learning of LLMs via Knowledge Consolidation and Decoupling
Maoqi Liu, Quan Fang and Yufei He
Continual learning (CL) is essential for Large
Language Models (LLMs) to sequentially adapt to evolving tasks. To mitigate catastrophic forgetting, recent advances implement low-rank adaptation with orthogonal projections (e.g., O-LoRA) to isolate task parameters. However, we reveal that such strict
geometric constraints trigger an "Orthogonality Dilemma": rigid parameter isolation impedes the transfer and accumulation of shared representations across semantically related tasks. In this work, we propose a new replay-free method, called Consolidation and Decoupling LoRA (CoDe-LoRA), for CL of LLMs. CoDe-LoRA disentangles the learning process into Consolidating Universal Knowledge and Decoupling Task-Specific Knowledge. To achieve this, CoDe-LoRA leverages an adaptive null space projection mechanism and semantic routing to balance knowledge accumulation with task-specific adaptation. Experimental results across four backbones and three CL
benchmarks show that CoDe-LoRA achieves the best average accuracy. Our code is available at https://github.com/Estrellajer/CoDe-LoRA.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Mitigating Concept Drift in QoS Prediction for Teleoperation of Autonomous Vehicles Using Historic Data
Xiyan Su, Jianning Gao, Mahmoud Ashri et al. (+1 more)
Teleoperation serves as the fallback solution to autonomous driving but reliable functions of the teleoperation require a certain amount of mobile network resources, which cannot be guaranteed at all times. Therefore, predictive quality of service (pQoS) is introduced as a concept to increase the resilience of the teleoperation. In this paper, based on a data measurement campaign, we propose a prediction framework to prediction two important network KPIs of teleoperation: uplink data-rate and round-trip latency. Furthermore, we introduce a method to alleviate the performance degradation of machine-learning-based prediction models on previously unseen data due to concept drift by incorporating historic data into the prediction pipeline. Additionally, we introduce the metric of critical scenario detection to evaluate the prediction performance specifically for teleoperation.
Read the full abstract ▾
All authors Xiyan Su, Jianning Gao, Mahmoud Ashri, Frank Diermeyer
Artificial Intelligence · Cross-listed from cs.DC
DySCo: Dynamic Sharding for Collaborative Edge-Cloud LLM Inference with Depth-Synchronized Batching
Jingpo Xu, Paul Joe Maliakel, Ivona Brandic et al. (+1 more)
Pervasive intelligent applications are increasingly deployed on mobile and Internet of Things (IoT) edge devices. Consequently, Large
Language Models (LLMs) are increasingly used to support these applications. Yet, due to their high resource demands, LLMs are mostly deployed in the cloud. Layer-wise edge-cloud inference lets resource-constrained edge devices contribute computation to LLMs they cannot host in full. However, heterogeneous split points introduce two coupled inefficiencies. First, edge execution and communication create idle gaps between cloud invocations. Second, requests arriving at different model depths cannot be conventionally batched. We present DySCo, a collaborative runtime that keeps KV caches local and introduces dyForward, a model-aware layer-range executor that runs configurable contiguous layer ranges from resident model shards without reloading weights. For multi-edge serving settings, we introduce depth-synchronized batching (DSB), which advances heterogeneous requests to the deepest cut and batches their common suffix. Experiments across heterogeneous devices, two model families, and local and wide-area links show that idle gaps increase the latency of subsequent GPU forward calls even when waiting time is excluded, adding up to 25 ms of additional cloud-side suffix latency per decoding step in our measurements. At an average concurrency of eight, DSB improves throughput by 275% over FIFO, 48% over exact-match batching, and 79% over round-robin interleaving while reducing mean per-session latency. Together, these results show that requests with different edge-cloud splits can reuse resident cloud weights and share batched suffix computation. The artifact repository for this work is publicly available at: https://github.com/Large-scale-Sustainable-Computing-LSC/dysco-artifact
Read the full abstract ▾
All authors Jingpo Xu, Paul Joe Maliakel, Ivona Brandic, Shashikant Ilager
Artificial Intelligence
zkLLMPoT: Efficient Zero Knowledge Proof of Training for Large Language Models
Junkai Liang, Zhanpeng Guo, Pengfei Wu et al. (+5 more)
Auditing the claimed outcomes of large
language model (LLM) training is challenging when model weights and training data are private, while cryptographically proving the full training process is prohibitively expensive at
Transformer scale. We present zkLLMPoT, a zero-knowledge framework that certifies auditor-defined properties of a trained checkpoint through forward evaluation rather than verification of its optimization trajectory. zkLLMPoT includes 2 phases: 1) The trainer fixes the architecture and the model weights are committed. Then the auditor selects challenge sequences, preventing the trainer from modifying the checkpoint in response to the audit data. 2) Then the trainer proves the objective value attained by the committed model on those sequences. This formulation makes the certification cost independent of the number of training iterations, without revealing model weights or requiring access to private training data. We build on sumcheck- and lookup-based arguments to certify
Transformer computations, while supporting next-
token loss and task-specific audit objectives. Across four model families, operator-level
benchmarks yield proving times of 41-59 seconds for 1.1-1.5B-parameter models and 131 seconds at 13B for the covered operators, with verification below half a second at a sequence length of 512.
Read the full abstract ▾
All authors Junkai Liang, Zhanpeng Guo, Pengfei Wu, Qingni Shen, Jiaheng Zhang, Zhonghai Wu, Haiyang Xue, Shengfang Zhai
Artificial Intelligence
MASC: A Multi-Agent Self-Calibration Framework with Latent Construct Alignment for Consistent Client Role-Playing in Psychological Counseling
Shixin Peng, Kun Jiang, Jiaxing Zheng et al. (+2 more)
Large
language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation requires clients to remain psychologically coherent across extended interactions. Existing role-playing methods largely rely on static profile
prompts and may exhibit persona drift, unrealistic cooperativeness, or inconsistent psychological states, communicative actions, and emotions. Existing evaluations also lack a unified testbed for both stable client characteristics and evolving psychological dynamics. We propose MASC, a Multi-
Agent Self-Calibration framework with latent construct
alignment for consistent client role-playing in psychological counseling. MASC combines construct-guided generation, collaborative refinement, consistency verification, and
memory-based revision in a closed calibration loop that detects and corrects inconsistencies as dialogue unfolds. We further introduce CRPC-Bench, a
benchmark covering session-level profile information and Big-Five personality traits, as well as turn-level psychological state, communicative action, and emotion expression. CRPC-Bench contains 38 motivational interviewing client profiles augmented with personality and emotion annotations. Experiments show that MASC outperforms existing methods across profile, personality, receptivity, and turn-level consistency, with the heterogeneous configuration achieving the strongest overall performance. MASC and CRPC-Bench provide a unified foundation for developing and evaluating psychologically coherent client simulations for AI-assisted counseling research and training.
Read the full abstract ▾
All authors Shixin Peng, Kun Jiang, Jiaxing Zheng, Qihao Yang, Jingying Chen
Artificial Intelligence
LeanPlan: Optimal Planning with LLM-Generated Heuristics and Admissibility Proofs
André G. Pereira, Augusto B. Corrêa, Felipe Meneguzzi et al. (+1 more)
Frontier large
language models (LLMs) can generate heuristic functions that guide search to achieve state-of-the-art performance in satisficing planning, where any plan is acceptable. However, these heuristics are not guaranteed to be admissible and can lead to suboptimal plans. We introduce LeanPlan, the first planning system that finds optimal plans with LLM-generated heuristics whose admissibility is machine-checked. Given a domain description and training tasks, an agentic loop uses planner feedback to iteratively improve a reusable domain-specific heuristic, its admissibility proof and the required domain assumptions. LeanPlan implements the heuristic, its proof and an efficient planner with machine-checked grounding and search in Lean 4. We evaluate LeanPlan on ten domains from the International Planning Competition and three new domains, using test tasks with up to 57 times as many objects as the training tasks. With GPT-5.6 Sol in the agentic loop, we successfully generate heuristics and admissibility proofs for all these domains. With the resulting heuristics, LeanPlan usually expands fewer states than the state-of-the-art Scorpion planner and solves more tasks overall.
Read the full abstract ▾
All authors André G. Pereira, Augusto B. Corrêa, Felipe Meneguzzi, Jendrik Seipp
Artificial Intelligence
Sensor-Language-Action Models
Yuekai Xu, Zitao Shuai and Yuzhe Yang
Sensors are useful not only for understanding the world but also for deciding what to do next. Existing sensor models however largely stop at perception: they recognize states or predict outcomes, leaving actions modeled separately through task-specific and often closed label spaces. We introduce Sensor-
Language-Action (SLA) modeling, a framework that connects
multimodal sensor observations, natural
language, and actions within a unified model. SLA uses
language as a semantic interface between sensing and acting, allowing heterogeneous actions to be represented, predicted, and explained while remaining grounded in the underlying sensor evidence. We build a large-scale SLA
benchmark consisting of
datasets that span more than 116,000 individuals, 79 sensor modalities, and 60 action groups, together with a multi-faceted captioning pipeline that aligns user context, sensor dynamics, and action evidence. Building on this framework, we present OpenSLA, a unified SLA model for hierarchical action prediction, state understanding, and action explanation. Extensive experiments on real-world tasks in clinical prediction, operating rooms, and metabolic health verify its superior performance over the state-of-the-art. OpenSLA also demonstrates intriguing capabilities including
language-guided evidence grounding and zero-shot generalization to unseen actions and cohorts.
Read the full abstract ▾
Artificial Intelligence
OSFP4: Joint Optimization of Diagonal Smoothing and Block Scales for NVFP4 Quantization
Neriah Ben David, Ori Meir and Or Ordentlich
NVFP4 is an attractive datatype for large
language model (LLM) inference, offering compact storage and native tensor-core acceleration. However, preserving accuracy using NVFP4 requires careful quantization. In this work we develop a novel quantization scheme called Optimized Smoothing and Scaling for NVFP4 (OSFP4). For each linear projection it uses a diagonal smoothing
matrix whose entries are optimized to minimize the squared
matrix-product quantization error under NVFP4, taking into account the rounding procedure that is used (either round-to-nearest, or GPTQ-style successive interference cancellation). This requires performing joint optimization on the smoothing entries as well as the block scales, which is facilitated by analyzing a multiplicative-dither FP4 quantizer instead of the fixed deterministic one. Experiments show that OSFP4 achieves the highest average accuracy among the evaluated competitors in the corresponding quantization settings, while retaining approximately 94-97% of vendor NVFP4 prefill throughput on the measured workloads. Our code is available in https://github.com/neriahbd/OSFP4
Read the full abstract ▾
Artificial Intelligence
Confidence-Ordering Reversal under Contextual Priors in Neural Decoding
Xinyu Zhang and Sichao Liu
Contextual priors improve neural-to-
language decoding by reshaping candidate scores. However, confidence is read from the same reshaped scores, so the errors a prior leaves behind can become more confident with no change in accuracy to reveal it. We study how a prior shapes confidence in
speech retrieval on MEG-MASC and MOUS using local decoding scores, a contextual prior combined by additive shallow fusion, and the fused top-two margin as confidence. Among initially incorrect predictions, we find a confidence-ordering reversal: a larger margin makes a repair more likely when the correct candidate starts near the top of the local ranking, but less likely when it starts lower. On MEG-MASC, pooled correctness AUROC is 0.87, yet AUROC separating repairs from residual errors falls from 0.70 at initial ranks 2-3 to 0.39 at ranks 21-50. Errors starting beyond rank 20, inside the reversed region, make up 46.6% of all post-fusion errors. We propose a score-level account: a repair must first close the correct candidate's initial deficit, limiting its final margin, whereas a residual error can build a large margin between two incorrect candidates. A causal intervention that changes only the fusion weight moves the reversal to deeper ranks as predicted. Under a word-level LM prior, it keeps moving after accuracy gain peaks, so a weight chosen for accuracy does not settle confidence. Reading local and prior scores separately improves selective decoding: the decoder answers on 74.5% of windows instead of 56.7%, while 92% of output sets still contain the correct candidate. Confidence after contextual fusion should retain the local and contextual evidence behind each prediction, not just the fused scores. Project website: https://confidencereversal.github.io/; Code: https://github.com/AmadeusFake/NeuDecodingConfReversal
Read the full abstract ▾