Artificial Intelligence · Cross-listed from cs.DB
Bounded Semantic Planning and Deterministic Compilation for Reliable Enterprise Text-to-SQL
Yi Ai
Direct text-to-SQL asks a
language model to do two jobs: interpret the business question and construct the complete relational query. In enterprise schemas, SQL can execute successfully while using the wrong relationship role or aggregation grain. We study an alternative placement of the
stochastic boundary. A multi-turn planner grounds phrases and selects from question-specific governed options; graph traversal, role predicates, grain lowering, SQL construction, and deterministic checks are implemented in code. We evaluate this semantic path compilation (SPC) system against direct DDL-to-SQL generation on the ACME insurance
benchmark. On a 38-question adjudicated comparison set with three runs per question, SPC was adjudicated correct on every run for 37 questions (97.4%), compared with 21 (55.3%) for the baseline. The paired discordance was 16 questions in favor of SPC and none in favor of the baseline (two-sided exact McNemar p=3.05x10^-5). SPC answered all 38 questions correctly at least once and produced one refusal and no adjudicated wrong-but-executed run across 114 run outcomes; the baseline produced 29 adjudicated wrong runs and seven additional judge-flagged data-only coincidences on the same set. A strict-equivalence sensitivity analysis increased the paired difference. Additional SPC runs with GPT-5.4 and Gemini-3.6-Flash showed similar question-level robustness, although their per-run verdict artifacts were not preserved. Six additional
benchmark items are retained in an all-item analysis and documented separately by failure class. The study supports an end-to-end systems result, not a causal claim that compilation alone produced the gain, because SPC receives governed semantic artifacts that the DDL baseline does not.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Hoeffding adaptive splitting trees for data stream classification with concept drift and ensemble learning
Daniel Nowak Assis, Jean Paul Barddal and Fabrício Enembreck
Ensembles of decision trees are well-established methods for data stream classification. In ensemble learning, Hoeffding Trees are widely adopted as base learners, performing periodic split attempts according to the Hoeffding bound. Recent studies, however, indicate that this standard splitting mechanism lacks adaptability, while adaptive trees that trigger splits in response to performance degradation have achieved superior results. In this paper, we identify limitations in the use of adaptive-splitting decision trees as ensemble base learners, showing that change detectors often fail to promote sufficient diversity within ensembles. To address this issue, we propose two novel decision tree models, termed Hoeffding Adaptive Splitting Trees. These models combine the periodic splitting strategy of Hoeffding Trees, which fosters ensemble diversity, with adaptive splitting mechanisms that employ change detection
algorithms to identify performance decay and determine split points. Experimental results demonstrate that Hoeffding Adaptive Splitting Trees enhance ensemble performance and achieve state-of-the-art results across a comprehensive evaluation, including
benchmark comparisons, computational cost analysis, and concept drift adaptation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
X$^2$Localizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localization
Zichao Zeng, Weijia Fan, Yufan Chen et al. (+7 more)
Cross-view
Video Geo-localization (CVG) aims to localize ground-view
videos by retrieving their corresponding geo-tagged aerial images. However, CVG approaches rely on fixed-length inputs and post-hoc refinement, hindering online-oriented localization under partial or dynamic observations. In this work, we formulate Progressive Cross-view
Video Geo-localization (PCVG) as a deployment-oriented extension and evaluation protocol of CVG, enabling localization under varying temporal budgets, prefix-based inference, random-start evaluation, and long-range localization with interruptions. To explore PCVG, we introduce X$^2$Localizer, a cross-grained
alignment framework that jointly supervises global prefix-to-aerial
retrieval and
token-aggregated frame–aerial-tile matching with a budget-dependent asymmetric objective. Furthermore, we introduce a Sliding-Window Re-Localization (SWRL) strategy that dynamically refreshes candidate regions for failure recovery and long-range deployment without full-sequence reprocessing. Extensive experiments show that X$^2$Localizer preserves conventional full-
video performance, with marginal gains of +0.1 Recall@1 and +0.3 Recall@10, while substantially improving early localization. In the challenging single-frame setting, X$^2$Localizer improves coarse
retrieval by +4.7 Recall@1 and +11.5 Recall@10 over the previous state-of-the-art method. With SWRL, our approach further enables robust progressive localization under random-start and long-distance scenarios, narrowing the gap between
benchmark evaluation and real-world deployment.
Read the full abstract ▾
All authors Zichao Zeng, Weijia Fan, Yufan Chen, June Moh Goo, Junwei Zheng, Ruiping Liu, Kunyu Peng, Jiaming Zhang, Rainer Stiefelhagen, Jan Boehm
Artificial Intelligence · Cross-listed from cs.RO
Orbit-Planner: Towards Latent World Models for On-Orbit Obstacle Avoidance of Satellite Agents
Zhijian Li, Chao Ren, Peijin Wang et al. (+1 more)
Satellite
agents for on-orbit
navigation tasks need to predict collision risks using limited onboard observations. However, conventional planners often rely on predefined maps and fixed environmental assumptions, limiting their adaptability in dynamic on-orbit scenarios. In this paper, we propose Orbit-Planner, a two-stage latent world model for on-orbit obstacle avoidance. Orbit-Planner learns action-conditioned spacecraft dynamics to perform future-state rollouts in latent space, and introduces a Physics Probe to decode physical state changes from imagined latent trajectories. Experiments demonstrate that Orbit-Planner can perform long-horizon latent rollouts and recover physical states from imagined trajectories. In closed-loop obstacle-avoidance
navigation in Isaac Sim, it attains a success rate of 91.7%. Code is available at https://github.com/ZhijianLi2003/Orbit_Planner.
Read the full abstract ▾
All authors Zhijian Li, Chao Ren, Peijin Wang, Xian Sun
Artificial Intelligence
Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies
Shaolong Chen, Yanlin Fei, Nazhou Liu et al. (+7 more)
Can a
language model recover the true research idea of a published paper when given only that paper's pre-publication bibliography? We introduce Reconstruction, a blind idea-recovery
benchmark that withholds the seed paper and all contemporaneous or future literature, and asks models to propose hypotheses that an independent large
language model judge matches against the held-out ground-truth idea. A strict anti-leakage protocol-temporal citation cutoff, anonymous reference IDs, and frozen per-paper bibliographies, which prevents
prompt-time leakage of the seed idea. Across six scientific domains and 643 evaluated papers, seven frontier models achieve only modest Match rates (approx. 3-15%). We then evaluate a reference-only multi-
agent (top 4) pipeline that combines cross-model review with a Swiss tournament over aligned hypothesis slots, without external web search. Cross-model review plus tournament selection raises Match rates to approx. 23-42% across all six domains, which is an observed approx. 2.4x lift over the best single-model baseline. This draft reports the protocol, anti-leakage design, and current results as an arXiv timestamp.
Read the full abstract ▾
All authors Shaolong Chen, Yanlin Fei, Nazhou Liu, Xinmiao Yu, Lei Li, Rahul Thapa, Madalina Ciobanu, Navan Preet Singh, Qingqing Mao, Ritankar Das
Artificial Intelligence · Cross-listed from cs.CL
Toward Better Assessment of LLMs' Performance in Clinical Error Detection
Yifan Zhang and Rahmatollah Beheshti
Automated detection of errors in clinical documentation is a promising application of large
language models (LLMs), yet decisions to deploy such models rest on
benchmarks that evaluate each clinical note in isolation. Error-detection
benchmarks are typically constructed by injecting errors into notes, such that each erroneous note has a natural counterpart. Aggregate discriminative metrics (e.g., balanced accuracy or F1) do not exploit this structure. We show that this omission is consequential. In particular, evaluating 15 diverse LLMs on 4 standardized clinical error-detection test sets across 3
languages, we find that 13 of 15 models fall below the level of random pairwise discrimination, even while achieving F1 scores that standard practice would read as moderate. We also observe that the underlying bias patterns differ across
languages: the same model can default to "no error" on one
language and over-flag errors on another. To diagnose where discrimination breaks down, we further introduce a procedure to score the evidence models cite in their outputs. We find that while models consistently locate error-relevant content, they fail to produce the corresponding correct verdict on the clean counterpart. Finally, we show that F1 and pairwise accuracy are driven in opposite directions by the same underlying bias, so that ranking models by F1 may systematically promote the weakest discriminators. For safety-critical clinical NLP applications, we advocate for supplementing aggregate metrics with paired evaluations in
benchmark reporting. Code and analysis scripts are available at https://github.com/healthylaife/paired-clinical-eval.
Read the full abstract ▾
Artificial Intelligence
PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning
Veit Laule, Jiangtao Shuai, Manfred Hauswirth et al. (+1 more)
LLMs remain unreliable for long-horizon planning, often generating logically inconsistent or non-applicable plans. Recent hybrid methods instead translate natural
language into the Planning Domain Definition
Language (PDDL), allowing symbolic planners to produce verifiable plans. However, existing methods frequently rely on rigid generation pipelines, a partial PDDL definition, or human feedback. Furthermore, their evaluation is hindered by the lack of standardized
benchmarks with automated verification. To address these limitations, we present PDDLCoder, an agentic framework for PDDL generation from natural
language that iteratively generates, analyzes, and refines planning specifications. We further introduce NL-pddlgym, a
benchmark dataset comprising 711 planning problems across 23 domains with executable gym environments for the automated verification of plan applicability. Experiments on the NL-pddlgym test set containing 106 problems across 4 held-out domains show that PDDLCoder generates applicable plans for 89.6% of tested planning problems. This improves upon our adaptations of previous PDDL generation methods, which achieved up to 45.3%, and outperforms direct LLM planning approaches, which reached up to 74.5% on the same test set. Our work demonstrates the effectiveness of agentic PDDL generation for planning and establishes a reproducible
benchmark for future research on LLM-assisted symbolic planning.
Read the full abstract ▾
All authors Veit Laule, Jiangtao Shuai, Manfred Hauswirth, Sonja Schimmler
Artificial Intelligence · Cross-listed from cs.SE
The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks
Bardia Mohammadi, Lars Klein, Aman Chadha et al. (+2 more)
Repository-scale coding requires an
agent to keep tests, imports, configuration, and migration rules consistent within a bounded context window. We model this as reconstructing a coupled-fact graph: at each edit, a required fact comes from recent context or parametric
memory, and the facts covered by neither form coherence debt. We supply and withhold each channel and inject faults across seven models and five harnesses. As expected, no model completes a task on an unseen API with both channels empty, and putting the facts in the
prompt restores success. When a rename defeats what models memorized about a real library, all seven fail in the same place, passing and missing the same tests. Availability decides the outcome and distance does not: withholding a fact costs exactly the work it supports, and a supplied fact works as well far from the edit as next to it. Harnesses pay unequal prices for it: configurations that all pass every test differ more than tenfold in
tokens consumed because they rebuild the same content at different rates, and spending more recovers nothing when facts are withheld. A missing fact produces wrong work rather than absent work: an
agent asked to act acts, fabricating the file or guessing the value, so instruments built on reads look for a hole already filled. How often it says it is blocked instead is a property of the model, from every trial to none. Availability does not settle every edit: where standard and code disagree,
agents follow the standard even when it prescribes the worse code, so a stale convention file costs more than no file. Because parametric
memory substitutes for reading, on SWE-bench, where models likely know the repositories, reads no longer predict success. Harnesses should keep the facts an edit depends on available when the
agent writes, and check that availability against what the
agent produces rather than what it reads.
Read the full abstract ▾
All authors Bardia Mohammadi, Lars Klein, Aman Chadha, Akhil Arora, Laurent Bindschaedler
Artificial Intelligence
Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement
Shenao Chen, Yidan Xu, Xiangmin Han et al. (+5 more)
Modern
Multimodal Retrieval-Augmented Generation (M-RAG) systems are fundamentally limited by the binary connectivity paradigm of traditional simple graphs, which fails to capture the intricate, high-order correlations among heterogeneous entities, such as the N-ary relationships between a visual chart, its scattered textual descriptions, and underlying numerical data. Furthermore, existing refinement strategies often rely on exhaustive, full-page reconstruction to align cross-modal information, leading to prohibitive computational redundancy and the introduction of contextual noise in long-form document processing. In this paper, we propose Hyper-M2RAG, a novel framework that redefines
multimodal document
retrieval through High-order Hypergraph Representation Learning. We first formalize the document structure as a
Multimodal Hypergraph, utilizing hyperedges as unified semantic containers to encapsulate multi-way associations across text, images, and tables, thereby transcending point-to-point modeling. To mitigate semantic fragmentation caused by physical pagination, we introduce an Anchor-driven Incremental Refinement mechanism. Rather than performing a global sweep, our approach identifies boundary-crossing anchor nodes and reconstructs their local hyper-
topology using one-hop neighborhood contexts. This targeted refinement effectively bridges cross-page knowledge gaps with minimal computational footprints. Extensive evaluations on
multimodal benchmarking
datasets demonstrate that Hyper-M2RAG significantly outperforms state-of-the-art methods in both
retrieval precision and generation coherence. Our code is available at https://github.com/ShenAoChen2001/MMHRAG.
Read the full abstract ▾
All authors Shenao Chen, Yidan Xu, Xiangmin Han, Rundong Xue, Duanpo Wu, Yuhan Gao, Chenggang Yan, Yue Gao
Artificial Intelligence · Cross-listed from cs.CL
When Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness
Mahdi Dhaini, Adam Dejl, Juraj Vladika et al. (+3 more)
Natural
language explanations (NLEs) are increasingly used as inputs, for example, as few-shot rationales that influence model behavior in in-context learning (ICL). However, it remains unclear how different types of NLEs compare in their effects on downstream model performance in explanation-augmented prompting. Therefore, we provide a comparative evaluation across six
benchmarks and four instruction-tuned models, studying how NLE source (human-written when available, self-generated explanations, generated by an external LLM) and NLE selection (random vs faithfulness-based filtering) affect downstream utility of NLEs when used in ICL settings. Our extensive evaluation shows that, on classification-style
benchmarks, adding NLEs to few-shot
prompts often improves accuracy over few-shot prompting without explanations; among NLE sources, externally generated LLM-NLEs often provide strong downstream utility and remain competitive with human rationales where both are available, whereas self-NLEs are more sensitive to the selection strategy. On math
reasoning, the effects are more model- and source-dependent. We further show that faithfulness-based selection of self-NLEs yields small average gains overall, but can improve or reduce performance depending on the metric, task, and model. Different faithfulness metrics can disagree substantially, affecting which self-NLE examples are selected and their downstream predictive utility. Robustness tests with randomly swapped and out-of-distribution rationales indicate partial robustness, suggesting that semantic
alignment contributes to performance gains. Overall, our results provide insights for selecting and reporting explanations that influence model behavior in practical prompting pipelines.
Read the full abstract ▾
All authors Mahdi Dhaini, Adam Dejl, Juraj Vladika, Volkan Özer, Barbara Plank, Gjergji Kasneci
Artificial Intelligence
A Shop Floor Production Scheduling Case based on RFID-supported Smart Factory
Zhihui Chen, Yize Sun, Yuhao Dong et al. (+2 more)
Radio frequency identification (RFID) technology has been widely implemented for real-time data collection in manufacturing shop floors, which, in turn, can be used to support dynamic shop floor production planning and scheduling. Within such an environment, uncertainty in operation and production processes collectively contribute to the dynamicity in manufacturing, thereby hampering the scheduling system from achieving maximal utility. To highlight the importance of handling such uncertainty, this paper addresses the problem of dynamic shop floor scheduling for a real-life case smart factory equipped with RFID technology. Feasible production sequence mining and real-time processing rate estimation are conducted on RFID-collected production data to quantify the operation and production uncertainties. A deep reinforcement learning approach based on the RFID data analysis is then presented for shop floor production scheduling. Simulation studies based on real-life case data have demonstrated the feasibility and practicality of the proposed dynamic production scheduling framework. Specifically, it is observed that the proposed framework outperforms existing dispatch methods in terms of minimizing operation makespan, including first in first out (FIFO), last in first out (LIFO) and deep Q network (DQN).
Read the full abstract ▾
All authors Zhihui Chen, Yize Sun, Yuhao Dong, Zeyu Xiao, Ray Y. Zhong
Artificial Intelligence · Cross-listed from cs.CV
HarmTrace: Anchor-Calibrated Decoupled Optimization for Fine-Grained Target Identification in Harmful Memes
Yujia Li, Yiqun Zhang, Zihan Cheng et al. (+7 more)
Multimodal harmful meme detection is typically formulated as image–text harmfulness classification. A model may correctly predict harmfulness while misidentifying the attacked target or its supporting evidence. We therefore extend harmful meme detection with fine-grained target identification, asking what type of target is attacked, who is targeted, and where the target appears in the meme. The model predicts harmfulness for every meme and, for harmful memes, outputs the target category, target entity, textual mention, and visual region. To support this task, we introduce Meme3W, which unifies multiple public harmful meme
datasets and provides human-verified annotations for harmful instances. We further introduce Joint Record Accuracy (JRA), a strict record-level metric requiring the harmfulness label and all target-identification fields to be jointly correct. Experiments with representative
multimodal large
language models reveal a substantial gap between harmfulness accuracy and JRA. To narrow this gap, we propose HarmTrace, an anchor-calibrated decoupled optimization framework. HarmTrace strengthens target-entity supervision through entity-aware supervised fine-tuning. It then applies Conditional Target-identification Policy Optimization (CTPO) to decouple harmfulness and target-identification advantages, restricting target-identification optimization to label-correct responses for harmful examples. CTPO uses a Virtual Positive Anchor (VPA) as a fully correct reference for target-identification advantage normalization. HarmTrace improves both JRA and harmfulness accuracy across the evaluated backbones, with JRA on the Qwen3-VL-8B backbone increasing from 17.58% to 52.51%. Our code is publicly available at https://github.com/llly1234/HarmTrace-for-Harmful-Memes.
Read the full abstract ▾
All authors Yujia Li, Yiqun Zhang, Zihan Cheng, Yijie Huang, Tenglong Ye, Zihan Wang, Xiaocui Yang, Shi Feng, Yifei Zhang, Daling Wang
Artificial Intelligence
Cost Scales with Change, Not Corpus Size: Incrementally Maintaining an Evolving Semantic Substrate
Yusuke Takahashi, Kyle Wild and Asako Uraki
Retrieval-augmented and agentic question-answering systems increasingly re-derive the meaning of a corpus at query time. Put plainly, instead of re-deriving what a corpus means on every question, the work is done once when a document arrives and is thereafter merely consulted – a compiler, not an interpreter, of meaning. An alternative is to compile that meaning once, at ingest time, into a compact, queryable semantic substrate and maintain it as the corpus evolves. The central objection is maintenance cost: rebuilding a truncated singular value decomposition (SVD) on every change appears prohibitive, and a change of
embedding model seems to force a full re-
embedding. We argue and show empirically that maintenance cost scales with the amount of change, not corpus size. On a controlled synthetic pilot (dimension 256, rank 32, a corpus grown from 3,000 to 9,000 documents over 50 update events), incremental low-rank updates were 33.7 times cheaper per update than full re-SVD and 23.8 times cheaper cumulatively, while the incremental subspace tracked the full recomputation to within floating-point precision (maximum principal-angle drift below 1e-11 degrees; recall@10 = 1.0). An orthogonal Procrustes virtual axis update recovered 0.95 mean cosine to truly re-embedded vectors by re-
embedding only about 10 percent of the corpus. The results support maintaining, rather than repeatedly reconstructing, a semantic substrate.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning
Peng Du, Kiran Kamble, Rakshith Vasudev et al. (+5 more)
Palmyra x6 is a large
language model optimized for use with enterprise-oriented agentic tasks. The model was built by post-training a Mixture-of-Experts base model with Anchored Supervised Fine-Tuning on a compact corpus of verified, synthetic tool-use trajectories, optimized with a
Muon + Adam hybrid. The recipe is deliberately conservative and deliberately controlled: 626 trajectories, a single epoch, a low learning rate, and a KL anchor to the frozen base. The model shows substantial gains over the previous default model for Writer
Agent, and compares favorably with several recent models on public
benchmarks, scoring the highest on BFCL Core at $0.785$ and posts the highest six-
benchmark mean of the cohort. Furthermore, the model has shown itself to be competitive or leading relative to comparators in our bias and safety evaluations.
Read the full abstract ▾
All authors Peng Du, Kiran Kamble, Rakshith Vasudev, Zhizhuo Yang, Rohith Nadimpally, Arjun Krishna, Waseem Alshikh, Daniel M. Bikel
Artificial Intelligence · Cross-listed from eess.SP
Degradation-Aligned Self-Supervised Learning for State of Health Estimation of Lithium-Ion Batteries under Label Sparsity
Jiaqi Yao and Julia Kowal
An accurate estimation of the state of health (SOH) underpins safe and optimized use of the battery system. Although compelling, data-driven SOH estimation models typically require large amounts of high-quality labeled cycling data, while in practice such labels are often sparse in both quantity and coverage. Therefore, in this work, we propose a degradation-aligned self-supervised learning (SSL) framework based on a convolutional neural network-gated recurrent unit (CNN-GRU) model, which learns aging-consistent representations from unlabeled data through a cycle-order ranking objective as the pretext task for pretraining, thereby enabling robust SOH estimation after fine-tuning on sparsely labeled data. Test results showcase that the proposed ranking-based SSL approach proves to endow the pretrained model with degradation awareness from unlabeled data, and after fine-tuning the model can carry out accurate, robust SOH estimation, even when only an extremely limited amount of 1% of unevenly distributed labeled training data is available, where the MAE of 1.718% and RMSE of 2.329% can be achieved on the test
cell. In addition, in-depth analyses are presented regarding the influences of label distribution and cross-
cell robustness. We believe this work could shed new light on label-efficient SOH estimation of lithium-ion batteries, addressing a practical need in battery management.
Read the full abstract ▾
Artificial Intelligence
CACSurv: Concordance-Aligned Comparative Learning with Large Language Models for Cancer Survival Prediction
Tianqi Xiang, Qixiang Zhang, Xinpeng Ding et al. (+2 more)
Cancer survival prediction supports treatment planning, risk stratification, and follow-up management. Existing methods use structured clinical variables, whole-slide images, genomic profiles, or
multimodal inputs, while patient reports remain underexplored. We study report-centric survival prediction using reports that organize pathological, clinical, and molecular evidence. Large
language models (LLMs) can reason over such reports, but case-wise time regression introduces two mismatches. First, a formulation mismatch arises because survival evaluation depends on ordering comparable patients, whereas independent time predictions do not enforce ranking consistency. Second, a supervision mismatch arises because a censored patient's observed time indicates survival beyond that point and cannot serve as an exact regression target, although it still implies orderings relative to patients who died earlier. To address these mismatches, we propose CACSurv, a Concordance-Aligned Comparative framework for report-centric survival prediction. CACSurv reformulates survival modeling as mini-cohort comparative
reasoning, where an LLM predicts relative prognostic orderings. We introduce concordance-aligned rewards derived from comparable relations under right censoring, enabling censored outcomes to provide ranking supervision without exact event-time targets. At inference, Monte Carlo Reference Aggregation compares each patient with sampled references and aggregates positions into a cohort-level ranking. We establish TCGA-SurvReport, a
benchmark covering six TCGA cancer cohorts. CACSurv achieves the highest C-index on all six cohorts and an average C-index of 0.722, outperforming the strongest published survival model by 6.5 percentage points and the strongest LLM time-regression baseline by 4.2 percentage points. Our code, models, and
dataset will be available at https://github.com/xmed-lab/CACSurv.
Read the full abstract ▾
All authors Tianqi Xiang, Qixiang Zhang, Xinpeng Ding, Yi Li, Xiaomeng Li
Artificial Intelligence
Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents
Batu El, Jinhee Paeng, Fatih Dinc et al. (+7 more)
AI
agents increasingly operate as part of interacting systems rather than in isolation. As
agents exchange information and jointly make decisions, their interactions can improve collective
reasoning but may also produce herding, polarization, or amplify shared biases. Understanding and predicting these collective dynamics is therefore important for designing effective and aligned multi-
agent systems. Here, we study over 10,000 communities of
language-model
agents that repeatedly exchange messages and revise their opinions across objective mathematics questions and subjective political statements. Despite substantial diversity in possible behavior, the individual and group dynamics can be represented by three characteristic regimes: indifference, polarization, and consensus. AI
agents start indifferent and build conviction as they interact. On objective questions, communication improves collective accuracy, while on subjective questions it often drifts group opinions toward the right in the political spectrum. We explain these observations with a statistical-mechanics formalism in which
agents stochastically favor lower social pressure. Given only initial opinions, our model predicts individual trajectories, outperforms all standard baselines, generalizes to unseen community graphs, and reproduces the observed group archetype distributions. Our fitted model parameters reveal the mechanics underlying our key observations: i) communities operate below the critical social temperature, which explains conviction buildup; ii) attractive ties outweigh repulsive ones, which favors consensus; and iii)
agents holding the correct answer exert the strongest pull, which drives truth-seeking. Overall, our results demonstrate that collective behavior of AI
agents, like that of other complex systems, follows compact and predictive dynamical laws.
Read the full abstract ▾
All authors Batu El, Jinhee Paeng, Fatih Dinc, Shiye Su, Mete Erdogan, Aneesh Pappu, Haotian Ye, Wanjia Zhao, Surya Ganguli, James Zou
Artificial Intelligence
Probabilistic Circuits as Reasoning Machines in Artificial Intelligence (Part I)
Robert Peharz
This cumulative habilitation thesis studies probabilistic
circuits (PCs) as a powerful and tractable framework for
reasoning and learning under uncertainty in artificial intelligence (AI). It first advocates for probability as a core
language for AI, emphasizing its connections to logic and information theory; the conceptual simplicity of probabilistic
reasoning—based primarily on the sum and product rules; the parallels between probabilistic inference and human cognition; and the role of probability in optimal decision making. However, probability also faces significant computational challenges, as probabilistic inference is NP-hard in almost all probabilistic models. PCs address these challenges through structural constraints that ensure exact computation of a wide range of inference queries in
polynomial time, such as marginals, conditionals, most probable explanations, expectations, and more advanced inference tasks. This thesis synthesizes a decade of research across foundations, algorithmic developments, and empirical validation of PCs. Key contributions highlighted in this work are foundational theory of PCs,
Bayesian approaches for learning PCs, scalable implementations and integration with deep learning, hybrid models that combine PCs with intractable models, and connections with symbolic machine learning paradigms. This is the first part of my Habilitation Thesis. The second part is omitted, as it comprises the cumulative part of the thesis and has been published at various venues (see Chapter 5).
Read the full abstract ▾
Artificial Intelligence
CUBICS: Situation-aware performance estimation for safety-relevant ML components
Benjamin Herd, Jessica Kelly and Mario Trapp
Machine learning (ML) is a key technology driving innovation today, but ensuring ML safety remains a major challenge for safety-related applications. A promising idea is to build proven-in-use arguments from field data, e.g. by running ML components (MLCs) in shadow mode or within safety envelopes so that their outputs can be monitored as 'safe probes' without affecting safety. These probes can then be used to build a statistical argument about field performance in a
Bayesian way. However, many
Bayesian field-data approaches in safety engineering model failures as a simple Bernoulli (or binomial) process with a single global failure probability and i.i.d. trials, which is rarely adequate for MLCs whose performance depends strongly on context. Statistical evidence is also about coverage of relevant situations, including edge cases, and building a single integrated statistical model for the entire system is usually not feasible. To address these challenges, this paper introduces CUBICS, a context-modular framework for per-component, situation-aware performance estimation of safety-relevant ML components. CUBICS partitions the operational design domain into situations and, for each safety-relevant component, defines a set of situation-specific assumptions and probabilistic guarantees that are represented and updated in a
Bayesian manner using Subjective Logic (SL). By combining these guarantees with beliefs about how often each situation occurs, CUBICS derives an overall risk estimate for each component without requiring a monolithic system-level statistical model, and thus provides a building block for modular, field-data based safety assurance.
Read the full abstract ▾
Artificial Intelligence
DeepInsight II: One Trace from Benchmark to Robot
Siyi Li, Yuchen Kang, Wuliang Wang et al. (+4 more)
Across a Physical AI stack, evaluation maturity is inversely aligned with deployment risk: foundation models enjoy mature, standardized harnesses, while the
embodied layers on which deployment actually turns remain fragmented across
benchmark-specific simulators, embodiments, and interfaces. The first DeepInsight report (v1) unified evaluation across this stack behind three abstractions—task, resource, and result—but its quantitative evidence centered on the foundation-model layer;
navigation and manipulation (System 1) and whole-body control (System 0) remained simulation case studies, and physical execution was outside its empirical scope. DeepInsight II keeps that substrate fixed and quantifies the
embodied half. First, it reproduces released-checkpoint references across two
navigation and four manipulation
benchmarks under their native protocols. Second, MotionBench places four released whole-body controllers under one workload and metric contract, then carries a qualified within-family cohort from parallel simulation to matched real-
robot trials in which simulated and physical rollouts share a parent trace identity while retaining execution-domain-specific records, making the sim-to-real gap a native reduction rather than a reconciliation across toolchains. Third, a composed System 2–1–0 study extends trace localization into five evidence-grounded handoff labels, each mapped to a concrete repair action, with a measured repairability criterion and physical episodes testing the same attribution under hardware-observable state. The contribution is therefore not a new evaluation architecture, but empirical continuity from
benchmark execution to matched
robot evidence and repair-oriented diagnosis.
Read the full abstract ▾
All authors Siyi Li, Yuchen Kang, Wuliang Wang, Zhengjie Zhang, Jiangpin Liu, Jianhao Yao, Jie Chen
Artificial Intelligence · Cross-listed from cs.MA
VCE-Skill: Enhancing Skill Self-Evolution with Version-Change Experience
Jianming Chen, Xuanbin Ye, Yawen Wang et al. (+3 more)
Agents increasingly rely on reusable skills to encode task knowledge, tool-use procedures, and validation rules. Existing skill self-
evolution methods primarily revise skills using execution trajectories collected from current tasks, leaving the
evolution knowledge accumulated in public skill version histories largely untapped. Our pilot study reveals a clear complementarity between the two sources: public skill changes provide reusable
evolution priors, whereas trajectories provide evidence grounded in the current task. Motivated by this, we propose VCE-Skill, which distills noisy and implementation-specific public skill changes into reusable, structured version-change experience and adaptively fuses it with trajectory-derived proposals from the base evolver, thereby exploiting external experience while retaining task-specific evidence. Extensive experiments demonstrate that VCE-Skill improves skill self-
evolution, increasing mean scores by 3.20–4.98 points; transfer experiments further show that the resulting skills achieve stronger cross-model transfer performance. Our work highlights public skill version changes as a previously underexplored yet effective source of prior knowledge and advances trajectory-driven skill self-
evolution.
Read the full abstract ▾
All authors Jianming Chen, Xuanbin Ye, Yawen Wang, Junjie Wang, Qing Wang, Fanjiang XU
Artificial Intelligence · Cross-listed from cs.SD
Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization
Tony Alex, Wish Suharitdamrong, Sara Atito et al. (+5 more)
Large Audio
Language Models (LALMs) have made rapid progress on standardized
benchmarks, yet their deployment in practical media workflows, curation, archival indexing, and content distribution remains largely unrealized. We identify automated audio chapterization, the task of segmenting continuous audio streams into thematically coherent chapters, as a demanding and commercially consequential setting that exposes this gap. Chapterization is challenging because boundaries are defined less by objective acoustic events than by subjective editorial judgment, requiring models to reason sequentially over long acoustic contexts and approximate creator-authored boundary decisions. We present AudioChaps, a post-training framework for aligning end-to-end LALMs for this task via Group Relative Policy Optimization (GRPO) guided by Chain-of-Thought (CoT)
reasoning. To support training and evaluation, we curate three
datasets: AudioChaps-
Alignment, derived from creator-annotated chapter boundaries on YouTube; AudioChaps-CoT, which provides structured supervision for well-formatted, high-quality, and evidence-grounded boundary
reasoning; and AudioChaps-Eval, a held-out
benchmark for audio chapterization. Applying GRPO directly without a Supervised Fine-Tuning (SFT) cold start, AudioChaps-R1-Zero already improves average F1 by 33 points over the state-of-the-art LALM Audio-Flamingo-3-Think. The AudioChaps framework produces our final aligned LALM, AudioChaps-R1, which improves average F1 by 49 points. These results demonstrate that GRPO-trained LALMs can reliably transform unstructured auditory streams into navigable, structured media. Our code, models, and
dataset resources will be released upon acceptance at https://github.com/ta012/AudioChaps.
Read the full abstract ▾
All authors Tony Alex, Wish Suharitdamrong, Sara Atito, Armin Mustafa, Muhammad Awais, Philip J. B. Jackson, Jiankang Deng, Ismail Elezi
Artificial Intelligence · Cross-listed from cs.CL
When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation
Haolin Jin, Pengyue Yang and Huaming Chen
Retrieval-augmented generation (RAG) improves large
language models by grounding generation in external evidence, but it also introduces a source trust problem: retrieved context may be useful, irrelevant, or even misleading. Existing RAG systems often apply a fixed trust policy toward retrieved evidence, which can either over-trust incorrect context or underuse context when the user explicitly asks for context-following behavior. Therefore, we propose Intent-Guided Decoding (IGD), a framework that arbitrates between retrieved context and parametric
memory according to user intent. IGD uses answer-level filtering and
token-level correction to steer the final decoding trajectory between retrieved context and parametric
memory. We evaluate IGD on three faithful QA
benchmarks and three factual-conflict
benchmarks across five LLMs, IGD substantially improves factual recovery, achieving gains of up to 65.4 percentage points on factual-conflict
benchmarks over Direct RAG, while preserving or improving strict context-following behavior, this findings highlight the importance of balancing factuality and faithfulness in RAG.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans
Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani et al. (+2 more)
Human visual search is serial: the fovea must land on a candidate to confirm it, and those landings form a scanpath. Whether
multimodal large
language models (MLLMs), given the same foveated input, search as humans do bears on their use as models of human
vision and on
attention-
alignment scores. We compare three general-purpose MLLMs with human eye-movement scanpaths on goal-directed search (COCO-Search18), driving each model fixation by fixation through an identical, human-matched foveated view and assessing it along three axes: the decision of target presence, the efficiency of reaching the target, and the gaze process itself. The axes dissociate. On the decision and on target acquisition the models match or exceed humans, detecting present targets near ceiling and reaching them on the first saccade more often than people do. The gaze process is not human. Under the human-matched condition, all three share one signature: low-
entropy, large-amplitude, self-consistent scanpaths that agree with themselves far more closely than two humans agree with each other. That is consistent with a single-pass, non-serial architecture rather than a limit of acuity. Matched retinal input reproduces where humans look but not how the looking unfolds in time, and no degradation regime recovers human-like search at human-like success. The gap sits on a process axis that answer-
alignment and saliency metrics do not measure. Because they miss it, such metrics cannot certify human-like
vision, and zero-shot models suit outcome and spatial questions but not temporal, process-level ones.
Read the full abstract ▾
All authors Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani, Ulas Bagci, Alessandro Bruno
Artificial Intelligence · Cross-listed from cs.CV
MLLM-Guided Semantic Correction for Text-to-Video Generation
Junhao Chen, Zheqi Lv, Keting Yin et al. (+6 more)
Recent advances in
diffusion models and
Transformer architectures have led to significant progress in text-to-
video generation. However, these models often suffer from semantic errors such as missing objects, incorrect attributes, or mismatched actions. Although some semantic correction methods perform optimization before sampling or refinement after sampling, how to detect and correct semantic deviations during the
video generation process remains underexplored. In this paper, we introduce a training-free, interpretable mid-generation correction framework that integrates
multimodal large
language model (MLLM) feedback directly into the
diffusion sampling loop. Our framework achieves
diffusion trajectory correction by injecting semantic evaluation signals during
video synthesis, enabling the model to optimize the generated content through continuous self-reflection. We propose two key modules: a Semantic Assessment Supervisor that generates intermediate preview frames for semantic evaluations and deviation diagnostics, and a Semantic Modification Assistant that corrects semantic drift during inference via a controllable latent trajectory intervention. Our method improves semantic
alignment, visual fidelity, and temporal consistency without modifying model parameters. We validate the effectiveness of our approach through extensive experiments across multiple
benchmarks.
Read the full abstract ▾
All authors Junhao Chen, Zheqi Lv, Keting Yin, Shengyu Zhang, Zhou Zhao, Feiyang Chen, Xinyu Duan, Baoxing Huai, Fei Wu
Artificial Intelligence
Large language models as synthetic clinical experts to inform longitudinal rare-disease modeling
Clemens Schächter, Astrid Pechmann, Janbernd Kirschner et al. (+2 more)
Due to the limited amount of information, modeling longitudinal rare-disease data can benefit from integrating clinical knowledge. Yet, elicitation of expert knowledge and formalization for model fitting is challenging, in particular due to limited time of clinical experts. To nevertheless make domain knowledge accessible during model fitting, we use large
language models (LLMs) as synthetic clinical experts to supervise a variational-autoencoder-based approach that learns low-dimensional latent summaries of visit-level observations. Specifically, LLMs are queried offline on textual descriptions of patient observations to obtain judgments, e.g., the suspected clinical category. To improve the variational autoencoder fit, we train a differentiable surrogate model on these judgments and augment the loss function to encourage reconstructions that preserve the clinical-label distribution of their corresponding input profile. In an application to longitudinal motor-function assessments from children with spinal muscular atrophy, we map visit-level clinical profiles to low-dimensional representations that are linked by a multivariate mixed-effects model. The synthetic expert loss discourages reconstructions that remain numerically close in data space but alter the clinical interpretation of the reconstructed motor function profile, such as by crossing a disease-type boundary. We thus reduced disagreement between original and reconstructed SMA type labels from about 11 to 7 percent. Furthermore, informing the latent representation by the synthetic expert improved prediction of motor function milestones compared with unsupervised latent representations and a data-level baseline. These results suggest that incorporating LLMs into model fitting can make clinical knowledge available to representation learning and improve clinical faithfulness for longitudinal rare-disease data.
Read the full abstract ▾
All authors Clemens Schächter, Astrid Pechmann, Janbernd Kirschner, Jan Hasenauer, Harald Binder
Artificial Intelligence · Cross-listed from cs.RO
NebulaVLA: A Dual-Frequency Vision-Language-Action Model With Guide Action for Robotic Manipulation
Cong Zhao, Shuai Tian, Xu Zhang et al. (+11 more)
Real-world deployment of
Vision-
Language-Action (VLA) models is often bottlenecked by efficiency-performance trade-offs, cross-embodiment generalization, and execution smoothness. We present NebulaVLA, an asynchronous dual-frequency architecture that decouples high-level semantic
reasoning from low-level action control, optimizing computational resources and modularity. To bridge semantic gaps across heterogeneous
robots, we introduce GESTURE-7, a unified
language-grounded action representation. Furthermore, our Guide Action
algorithm enforces kinematic continuity via mask-based smoothness constraints. Comprehensive evaluations demonstrate that NebulaVLA significantly outperforms synchronous baselines, achieving an 85.5% average success rate on LIBERO-Plus and accelerating action generation by \textasciitilde 2.7$\times$. This asynchronous design enables highly efficient and responsive control for practical robotics.
Read the full abstract ▾
All authors Cong Zhao, Shuai Tian, Xu Zhang, Baocheng Ni, Xinguo Song, Xueying Sun, Shu Jiang, Shouchang Yang, Bo Tang, Jin Deng, Ge Zhu, YongCheng Wang, Jin Xu, Ri Yang
Artificial Intelligence · Cross-listed from cs.LG
Graph Machine Learning: An Opportunity for Power Systems
Martin Sadric, Sebastian Pütz, Christian Nauck et al. (+4 more)
Modern power systems face growing operational complexity driven by the integration of renewable energy sources, decentralization, and the need for real-time decision-making across a wide range of timescales. Addressing these challenges traditionally relies on model-based methods that, while accurate, can be too slow for operational demands. Machine learning (ML) has therefore emerged as a faster, data-driven alternative. As grid
topology plays a central role in power system operation, graph machine learning (GML) methods offer a natural framework for incorporating topological dependencies as an inductive bias. We survey nearly 800 papers at the intersection of GML and power systems, covering
forecasting, state estimation, optimization, control, fault diagnosis, and cybersecurity. Power systems constitute an unusually rich
benchmark setting for GML, as they combine hard physical constraints, multi-scale dynamics, safety-critical requirements, and scarce labeled data within a single, well-defined domain. Conversely, power systems can benefit from utilizing GML to complement classical solvers, as GML provide scalable,
topology-aware approximations with promising generalization and computational efficiency. We identify open challenges, including limited real-world deployment and the need for interpretable models in safety-critical settings. Despite the rapidly growing number of publications, standardized
benchmarks and open
datasets remain scarce, leaving many results difficult to reproduce and undermining the long-term scientific credibility of the field. We further derive a structured requirements catalog for ML-ready power grid
benchmarks, intended to guide future
dataset development and improve reproducibility across studies. We call on the community to prioritize dedicated
benchmark studies and the release of open
datasets and models.
Read the full abstract ▾
All authors Martin Sadric, Sebastian Pütz, Christian Nauck, Veit Hagenmeyer, Frank Hellmann, Dirk Witthaut, Benjamin Schäfer
Artificial Intelligence
Offline Reinforcement Learning for Hemodynamic Management of Sepsis in the ICU: a MIMIC-IV Study with Dual Off-Policy Evaluation
Marc Pérez-Roig, David Fernández-Narro and Carlos Sáez
The dosing of intravenous fluids and vasopressors in sepsis is a sequential decision made under uncertainty and guided largely by clinical judgment, which makes it a natural target for reinforcement learning from historical care. Because a learned policy cannot be trialed on patients, its value must be estimated off-policy, and such estimates can be fragile and optimistic. This work advances the reliable evaluation of sepsis treatment policies by combining off-policy estimation, reliability diagnostics, and clinician-agreement analyses in a transparent validation framework. We modeled fluid and vasopressor dosing on a cohort of 36,872 septic ICU stays drawn from the MIMIC-IV critical-care database, as a discretized Markov decision process with 1,000 states and 25 actions, defined by a five-by-five grid of fluid and vasopressor levels and solved by policy iteration. The clinicians' behavior policy was estimated with a random forest, which mitigated the collapse of the Effective Sample Size (ESS 50.1 against 4.0 with smoothed counts) that otherwise destabilizes the importance-sampling estimate. The learned policy was evaluated with two
estimators, weighted importance sampling (WIS) and fitted Q evaluation (FQE), with the ESS and clinician agreement as reliability checks. An empirical variable selection found that the composition of the state matters more than its size. Both
estimators place the learned policy above the clinicians' return (WIS 50.8 and FQE 46.8 against 38.2, ESS 50.1), yet it departs only modestly from observed practice (total variation 0.18), favoring less intravenous fluid. These retrospective single-center off-policy results support the learned policy as a clinically plausible refinement of observed practice and motivate its further evaluation as a discordance-based clinical decision-support approach.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
RISE: Roadside Infrastructure Sequence Understanding across 3D Tracking and Structured Vision-Language Reasoning
Yanbo Jiang, Haotian Zheng, Jiahao Wang et al. (+10 more)
We present RISE (Roadside Infrastructure Sequence Understanding and Evaluation), a framework spanning metric 3D tracking and structured
vision-
language reasoning in roadside sequences. For metric tracking, our image-only method combines SAM3
video identities with calibration-guided mask agreement for multi-view identity association, recovering persistent 3D tracks without
LiDAR or task-specific 3D training. Its calibration-conditioned geometry allows the procedure to be instantiated at different calibrated multi-camera intersections without layout-specific retraining. On 20 human-reviewed clips from six intersections, the generated tracks achieve 66.9 MOTA within the defined multi-view evaluation scope. For structured
vision-
language reasoning, a human-reviewed MLLM pipeline mines high-value clips and uses a constrained full-context Oracle to construct bbox-grounded predictive QA without exposing future evidence to evaluated models. The resulting RISE-VQA
dataset contains 33,910 QA pairs from 557 clips across 16 intersections and 61 roadside views. Its intersection-held-out RISE-Bench evaluates semantic choices, coordinates, future boxes, and interaction sets with deterministic task-specific metrics. Experiments show consistent benefits from domain adaptation and generally from temporal context, while revealing persistent challenges in spatial grounding, future localization, and interaction
reasoning.
Read the full abstract ▾
All authors Yanbo Jiang, Haotian Zheng, Jiahao Wang, Hanxiao Ren, Yitao Xu, Yining Xing, Zehong Ke, Hao Cheng, Yiqian Tu, Jinhao Li, Zhiyuan Xuan, Fang Zhang, Jianqiang Wang