AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

A Context-Aware Cultural Heritage Guide Powered by LLMs

Liliana Ardissono, Fabio Ferrero, Angelo Geninatti Cossatin, Claudio Mattutino, Noemi Mauro

We present an extension of Triangolazioni (a Cultural Heritage webapp) to enrich curated content with context-dependent, external information provided by Large Language Models (LLMs) within a loosely-coupled architecture agnostic to the LLM. The system supports context-dependent information search and presentation within an architecture agnostic to the exploited LLM.

arXiv

CURE: Local Uncertainty Repair for Block-Parallel Speculative Decoding

Aofan Liu, Jingxiang Meng, Fangxin Liu, Yongbiao Chen

Speculative decoding mitigates the latency of sequential generation in autoregressive Large Language Models (LLMs) by interleaving draft generation with target verification. However, existing parallel drafting backends often suffer from rapid accuracy degradation over long horizons, leading to high rejection rates during verification and suboptimal wall-clock speedups. We observe that drafting errors are not uniformly distributed but typically stem from localized high-uncertainty tokens that destabilize downstream generation trajectories. Motivated by this token error pattern, we propose CURE, a budget-aware dynamic repair tree designed to repair errors at uncertainty focal points without incurring prohibitive tree-verification overheads. Specifically, our method uses predictive confidence margins to dynamically locate candidate error tokens within a block-parallel draft, expands bounded repair paths only at these fragile nodes, and employs a novel repair resynchronization mechanism to realign draft states post-verification. Evaluations on code-generation benchmarks (HumanEval, MBPP, and LiveCodeBench-lite) and mathematical reasoning benchmark (GSM8K) demonstrate that CURE increases the average accepted length by 4.2-7.5% over parallel baselines without repair, translating to an end-to-end speedup of $2.66-3.49\times$ over target-only decoding. Furthermore, we provide a plug-and-play repair module compatible with standard parallel drafting frameworks. We also characterize the trade-off between draft compute and verification efficiency.

arXiv

SSTG-Nav: Metric-Grounded Spatial-Semantic Topological Graphs for Reusable Object Navigation

Daojie Peng, Bingtao Wang, Jun Ma

Service robots operating for months in the same homes, offices, and facilities should become more reliable with experience instead of searching familiar space from scratch for every request. Yet ObjectNav is predominantly formulated as one-shot exploration, leaving a central deployment challenge unresolved: recognizing an object does not identify a reachable place to stop, and one confident map error can terminate the task. We introduce SSTG-Nav, a reusable metric-semantic memory that turns a one-time survey into actionable object goals, consolidates evidence across viewpoints, and retains spatially distinct recovery standoffs. On 1,000 HM3D-v2 episodes across 36 scenes, our goal-independent topology achieves a 99.4% geometric success ceiling. Holding semantic responses fixed, metric grounding raises SR/SPL from 0.835/0.560 to 0.920/0.603, and source-aware fusion reaches 0.926/0.586. Fusion-aware Top-3 recovery raises Success@1/2/3 to 0.928/0.965/0.975 and reaches 0.601 SPL@3. Model, field-of-view, density, and corruption controls identify where these gains originate, and a ROS2/Nav2 realization demonstrates the complete reusable query-to-execution pipeline. Together, the results establish pre-exploration as a powerful practical regime for dependable, repeated semantic navigation.

arXiv

BayesSeg: A Bayesian Optimization Framework for State Segmentation of Electricity Consumption Time Series

Zhenya Zhang, Wendi Zhu, Ping Wang, Hongmei Cheng, Shuguang Zhang

In Non-Intrusive Load Monitoring (NILM), adaptive segmentation of electricity consumption time series is critical for appliance recognition. However, prevailing methods face challenges including heuristic parameter tuning, boundary sensitivity, and metric saturation. This paper proposes BayesSeg, a unified framework integrating time-series segmentation, multidimensional evaluation, and automatic parameter optimization. The segmentation layer employs a dual steady-state criterion based on the tail value and mean of preceding subsequences, combined with a sequential extraction and complement-set parsing strategy, to achieve precise unsupervised partitioning of steady-state and transition-state segments. The evaluation layer maps segmentation results to binary state sequences and formulates a composite metric integrating an event-level F1 score (event_F1) with Normalized Mutual Information (NMI). The event_F1 quantifies switching-event precision and recall via tolerance matching, while NMI captures global structural consistency, jointly overcoming the boundary sensitivity and limited discriminability of point-wise metrics. In the optimization layer, the composite score serves as the objective function for Bayesian optimization, which constructs a TPE surrogate model for efficient global parameter-space exploration. Experiments on the SustDataED2 dataset demonstrate that Bayesian optimization requires only ~100 objective evaluations to locate a parameter region within 0.35% deviation of the exhaustive grid-search optimum. The framework achieves a weighted composite score of 0.7149 and an event_F1 of 0.9340 while reducing optimization latency from ~5300 seconds to under 1 second, a speedup exceeding 5700x. BayesSeg automates segmentation configuration and provides a scalable, efficient solution for time-series analysis in NILM and related domains.

arXiv

TaPR: Test-Aware Policy Refinement for Feedback-Conditioned Code Generation

Aofan Liu, Jingxiang Meng, Fangxin Liu, Yongbiao Chen

Multi-turn code agents rely on execution feedback to repair incorrect programs, yet standard reinforcement learning paradigms optimize and evaluate policy performance primarily using single-shot outcome rewards. This misalignment conflates initial code generation with feedback-driven refinement, discards granular execution signals across intermediate turns, and fails to evaluate whether the policy actually acquires self-repair capabilities. We propose Test-aware Policy Refinement (TaPR), a framework that transforms execution feedback into a dense per-turn test-pass-ratio reward under a consistent multi-turn interaction protocol. Across six models on 219 code-generation problems from LiveCodeBench, TaPR improves the pooled three-turn success rate (Pass@3) by 2.44 percentage points. In the predefined 7B/8B high-headroom slice, pooled accuracy increases from 30.25% to 33.56% (+3.31 pp), with 42 improvements and 13 regressions in paired trials. On a matched Qwen3-8B ablation, the dense reward supplies nonzero feedback in all of the first ten steps and reaches a higher Hard-subset peak than outcome-only GRPO within the tested budget, although GRPO nearly matches pooled Pass@3 by step 300. Our primary contribution is a reward-decomposition framework and a turn-aware evaluation protocol that decouple first-shot generation quality from multi-turn repair competence.

arXiv

F-WANDA: Fisher-Reweighted Post-Training Pruning for Sustainable Deployment of Large Language Models

Himanshu Mishra

One-shot post-training pruning is the most energy-frugal compression strategy for largelanguage models (LLMs), yet existing approaches trade either quality (WANDA) or compute cost (SPARSEGPT). We introduce F-WANDA, a drop-in modification of WANDA that reallocates the per-row keep budget across output neurons in proportion to the empirical Fisher information of the pre-activation. The Fisher signal is collected in a single additional backward pass over the same calibration corpus WANDA already uses; no weights are updated. On LLAMA-2-7B at 50 % unstructured sparsity, F-WANDA attains WikiText-2 perplexity of 6.85, matches WANDA fluency, and improves 5-shot MMLU by +1.6 pp over WANDA and +1.1 pp over SPARSEGPT, while incurring only one-third of SPARSEGPT pruning wall-clock and energy. The headline trade-off is achieved without extra calibration data or fine-tuning, placing F-WANDA on the Pareto frontier of quality versus pruning cost for sustainable LLM compression.

arXiv

Ekova: A Personality-Support Agent for Self-Discovery Dialogue

Yuyan Chen

Emotional Support (ES) systems have long optimized a single objective: alleviating the user's emotional distress in the moment. We argue that a complementary need, helping users see themselves more clearly, defines a distinct paradigm we call Personality Support (PS). PS is not counseling or clinical intervention: it targets cognitive clarity and self-articulation, not symptom relief or diagnosis. We instantiate this paradigm in three layers. First, we present DSD, a Chinese self-discovery PS Dataset of 8,590 samples collected through real longitudinal interaction across five minimal units, Coach, Warm, Tsukkomi, Real, and Gonzo. Second, we build DeepSupport, a multi-persona PS system trained with OrthoTune, a PS-tailored framework with style-specific adapters and a style-consistency regularizer. Third, we unify the five DeepSupport personas into Ekova, a persistent personality-support agent with a unified cross-session memory layer, supporting both adaptive routing and user-customized persona selection. Experiments show that OrthoTune-trained models outperform all baselines with an average relative gain of 16.3% across all metrics over the strongest prompt-based baseline. Code is available at https://github.com/Yukyin/Ekova.

arXiv

CeQe: Grounding Lexical Retrieval in Semantic Evidence

Adam Kahirov, Umesh Deshpande, Swaminathan Sundararaman

Lexical retrieval (BM25) captures exact keyword matches and weights terms by corpus-wide significance, but it is blind to the semantic vocabulary gap: when a relevant document phrases an answer differently from the query, BM25 never retrieves it, and no amount of downstream reranking or fusion can recover a document that was never in the candidate set. We present Cross-Encoder Query Expansion (CE-QE), which reads the per-token relevance attributions of a cross-encoder applied to top semantic search results, selects the terms the cross-encoder treats as decisive, and appends them to the BM25 query. Unlike classical pseudo-relevance feedback, which reuses BM25's own (possibly wrong) top results, CE-QE seeds expansion from the semantic retriever's results, avoiding self-reinforcing query drift. Unlike recent generative query expansion (HyDE, Query2doc), which prompts a large language model to hallucinate text from its parametric knowledge, every CE-QE expansion term is copied verbatim from a retrieved passage, so it cannot introduce vocabulary the corpus does not contain, and its only added cost is attribution extraction on a cross-encoder a hybrid pipeline already runs for reranking. On seven BEIR datasets, CE-QE improves lexical recall substantially where query and answer vocabulary diverge (e.g., NQ Recall@100 from 0.32 to 0.47), and its score-fusion variant (SESF) beats cross-encoder score fusion by 2.5% on Recall@100 and beats SPLADEv2 and ColBERTv2 by 5.3% and 4.6% on nDCG@10, while leaving the underlying BM25 index completely unmodified.

arXiv

Distilling Reasoning Traces into Advisory Prompts for Software Engineering Tasks

Faizan Faisal, Prem Devanbu, Toufique Ahmed

Language models are widely used for generating and otherwise processing code (e.g., identifying code hallucinations, possible inputs, or predicting outputs); however, LLMs can make mistakes, which can be serious. One key issue is that models are trained on (still) largely human-written, and thus imperfect, code; it's not easy to find sufficiently large code corpora that are entirely free of bugs. Thus, other inference-time ways of reducing LLM errors, without additional training, are desirable. "Reasoning" or "thinking" modes, exposed as a togglable feature by hybrid reasoning models, do reduce errors; however, reasoning consumes additional resources. This paper asks if better performance can be achieved without always incurring the cost of reasoning. Human students of programming learn to avoid mistakes by (a) identifying them, (b) reflecting upon the cognitive lapses that led to them (essentially, "thinking through" the errors), (c) inferring general rules or lessons from these reflections, and (d) internalizing these lessons into rules. In tutorial sessions with an instructor, this is a common Socratic interaction. Examples of such internalizable rules might include the nugget "Before coding, restate the requirements to clarify them." Inspired by this process, this paper describes an approach where we first identify examples in which "thinking mode" in a (low-resource) LLM avoids errors. These errors, and their avoidance via "thinking" in the same LLM, are then examined by a bigger LLM to generate summary explanations; these are then summarized by a large LLM into brief advisory prompts. This approach works on many modest-sized models; in some cases, the "advisory prompts" thus learned can also be gainfully transferred to other models. We also present investigations into the nature of coding errors that language models make, and a characterization of when this approach can be helpful.

arXiv

Diagnose Before You Compress: Prediction-Independent Bottleneck Witness Refinement for LLM Serving Traces

Liming Liu, Chao Hu, Mingfei Lu, Cong Tan, Yiwei Ge, Chijin Zhou, Yongjun Xie, Runzhe Wang, Xiaohai Shi, Heyuan Shi

Production LLM serving generates millions of diverse requests, making full-trace replay across serving configurations increasingly expensive. Existing trace reduction methods mainly preserve workload distributions or representative requests, but bottleneck-revealing workloads may be rare and non-representative. Moreover, evidence for one component cannot compensate for missing evidence in another, while using predicted bottlenecks as target truth creates circular evaluation. These limitations make it necessary to preserve evidence for every bottleneck component rather than rely on workload representativeness alone. We propose Bottleneck-Preserving Witnessing (BPW), a quality-constrained framework for compact and diagnostically reliable LLM serving replay suites. BPW first performs Workload Candidate Nomination using response-blind workload features and closed source-side measurements. This stage identifies workloads that may expose scheduler, prefill, decode, or KV-cache bottlenecks. Coverage-Priority Sequence Construction then organizes multi-component proposals as reusable hyperedges and prioritizes weak and uncovered dimensions. Finally, Bottleneck Truth Verification derives prediction-independent labels solely from direct target-system measurements. The verified results determine the earliest prefix satisfying the direct two-witness requirement for every component. Experiments on BurstGPT, ServeGen, and Mooncake show that BPW reaches the verified gate with a compact workload set and outperforms 16 policies, achieving relative improvements of 2.3% and 16.3% in Mean prefix Macro-F1 and WBRC-AUC, respectively. Stage-resolved and sensitivity analyses confirm the distinct contributions and local stability of its three stages. Our code is publicly available at https://github.com/llmllmllm/BPW

arXiv

Mask-Based Priors Are More Persistent than Query-Key Initializations

Mingze Ma, Hemanth Saratchandran, Cameron Gordon, Simon Lucey

Transformers do not merely lack data on some Boolean extrapolation tasks; they generalize in a systematically wrong way. Recent work on generalization on the unseen has shown that, despite fitting the observed domain, Transformers often extrapolate according to a simpler minimum-degree interpolator rather than the true target function. These Boolean tasks are not practical applications, but controlled stress tests for understanding Transformer inductive bias. We ask whether this failure mode can be corrected by injecting explicit structural priors into attention. Existing structured-initialization methods alter Transformer inductive bias indirectly, by choosing query and key projections whose similarity scores approximate a desired attention pattern. However, we find that when applied to Boolean extrapolation, these QK-based priors can be rapidly overwritten during training and fail to change the learned extrapolation rule. We propose a simpler alternative: initialize the additive attention mask directly. Unlike standard hard masks used for causality or locality attention, our mask is a finite, learnable attention-logit bias initialized from task-level interaction structure. This separates the structural prior from content-dependent attention scores, allowing it to persist throughout optimization. On Boolean reasoning tasks, mask-based initialization achieves near-perfect extrapolation where vanilla and QK-initialized Transformers remain trapped by the default inductive bias. The same mechanism also improves low-data arithmetic performance and remains competitive on vision and language benchmarks. These results show that attention masks can serve not only as architectural constraints, but as a simple substrate for encoding persistent inductive bias in Transformers.

arXiv

Gene Ontology-Guided Hierarchical Spatial Gene Expression Prediction from Histopathology Images

Zhiwen Xu, Xiaoming Yan, Chengkun Wu, Juan Chen, Haoang Chi, Liyang Xu

Predicting spatial gene expression from histopathology images enables large-scale transcriptomic profiling without the cost of direct measurement. Existing methods decode the target gene set as a flat, unstructured vector, ignoring the inter-gene dependencies arising from shared biological pathways and regulatory programs. Without explicit structural guidance, models must infer these dependencies entirely from limited paired data, constraining prediction quality. We propose MSGR (Multi-Scale Gene Refiner), which bridges this gap by incorporating the Gene Ontology (GO), a curated functional hierarchy of genes, as an explicit structural prior. MSGR organizes target genes into a four-level GO tree. Its GO-guided decoder then progressively refines predictions from coarse functional domains to fine individual genes via residual corrections under scale-weighted supervision. Operating solely on the gene side, the GO-guided decoder serves as a seamless plug-in replacement that consistently improves existing architectures without requiring any image-side modifications. Extensive experiments on nine datasets from the HEST-1k benchmark provide empirical evidence for two central claims: GO-structured decoding consistently outperforms flat decoding, even against a state-of-the-art generative baseline, and the gain is attributable to biological ontology structure rather than hierarchical decomposition per se, as confirmed by a +0.027 margin over a structurally equivalent random hierarchy.

arXiv

Verifiable Checks for Business Rule Consistency

Joseph Tafese, Milad Hooshyar, Sam Bayless, Nick Feng, Arie Gurfinkel

Maintaining consistency between natural language documentation of business rules and their evolving internal implementations is a significant challenge in large-scale systems. We present SIRNA, a tool and framework for checking such consistency using SMT solvers. Using the case study of cost calculations in tax domains, we demonstrate a three-part system that combines large language models (LLMs) with formal verification methods. SIRNA translates natural language documentation into candidate SMT formulas using LLMs, followed by checks to validate the translations. Then, corresponding business rules are converted into equivalent SMT representations and validated against the natural language formalizations. Our method is generalizable to domains where business logic exists in both natural language documentation and programmatic implementation. Compared to baseline evaluations, SIRNA significantly reduces the number of false positives and false negatives while offering explainability for its findings.

arXiv

The Gate, Not the Cache: Gate Provenance Bounds the Closed-Loop Reliability of Training-Free VLA Token Skipping

Qi Luo, Shuaijun Liu, Hao Zhao, Kunlin Li, Xiaobo Wang, Ningxing Su, dongsheng wang, Yun Chen

Token skipping is a widely used training-free way to accelerate vision--language--action (VLA) models by bypassing computation for most visual tokens at each control step according to a gate. When the next gate is harvested from the previous accelerated forward, however, the tokens skipped at one step are also the ones least visible to the next gate, and the damage can compound across control steps until the task fails. We study the two mechanisms this class is built on, reuse and deletion, crossing each against where its gate signal comes from on identical episodes. At a skip ratio of 0.9 on LIBERO-Object, both collapse when the gate comes from the model's own accelerated forwards, to 0.68 under reuse and to 0.31 under deletion against a dense 1.00, and the collapse is invisible to the action-level detectors we evaluate. What separates collapse from dense-level operation is not the mechanism but whether the gate is clean, computed by a forward that skipped nothing. We therefore propose actuation-slack refresh, one dense pass run while the robot executes its current action chunk, off the critical path, that hands the next step a clean gate and a fresh KV base. Since the measured detectors do not reliably reveal the failure, the refresh is unconditional rather than triggered. Both mechanisms then recover to 0.98, keeping the speed of skipping and the information of a dense pass. We then integrate the refresh into state-of-the-art caching and pruning methods across two VLA policies, 4 LIBERO suites, and 4 SIMPLER tasks, where it repairs every collapse caused by using a self-harvested gate. Serve latency drops 18--22\% below dense, measured both in simulation and on a physical robot. Where the gate signal comes from, not how tokens are skipped, decides closed-loop reliability for accelerated VLAs.

arXiv

Tensor Probabilistic Model Checking of Finite-Horizon Markov Chains (Extended Version)

Jianlin Li, Nick Guo, Peter Ye, Yizhou Zhang

We reexamine the problem of verifying Markov chains with respect to step-bounded reachability probabilities. Prevailing approaches rely on encoding the state-transition matrix using either explicit or symbolic representations. While these approaches are effective for sparse transition dynamics, they scale less favorably in the dense regime. Our insight is to cast probabilistic model checking of Markov chains as computations over dense tensors. This methodology enables the use of off-the-shelf compiler toolchains for optimized execution of these tensor computations on hardware accelerators. We prove the soundness of the methodology of mapping probabilistic model checking to tensor computations. We implement our approach in a tool called Tessa . Empirical evaluation shows that Tessa unlocks massive speedups over state-of-theart methods on selected benchmarks from the literature.

arXiv

Artificial Intelligence and Modeling & Simulation: An Overview

Niclas Feldkamp, Philippe J. Giabbanelli, Istvan David

Artificial intelligence (AI) and Modeling & Simulation (M&S) are increasingly intertwined, reflecting converging research needs across both communities, rapid technological advances such as the rise of generative AI, and the growing availability of data and computational resources. This report provides a structured overview of the intersections of AI and M&S. The relationship goes both ways: AI can support, augment, or even replace components of simulation studies, while simulations can serve as data generators, training environments, and evaluation platforms for AI. We organize this landscape along the stages of M&S from model specification and input modeling to execution, experimentation, verification and validation, and output analysis. Selected studies at each stage illustrates how techniques such as Large Language Models have reshaped simulation practices, while highlighting limitations and open challenges. This report also provides a conceptual roadmap that helps readers navigate a rapidly changing ecosystem.

arXiv

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response

Abu Bakar Siddik

Cyber-capable AI agents combine language models with tools, memory, and execution environments to perform multi-step offensive-security tasks. Existing work separately measures cyber capability and catalogs attacks against agent components, but provides less guidance on containing a capable agent within the environments used to evaluate it. This review synthesizes five vulnerability classes at that boundary: multi-step offensive chains, objectives that conflict with sandbox boundaries, supply-chain and credential exposure, persistent command-and-control, and the speed of automated action. We use two separate preliminary incident records: the reported July 2026 Hugging Face/OpenAI evaluation breach and Anthropic's subsequent three-incident evaluation review. A comparative evidence protocol distinguishes record-specific factual claims from the shared systems lesson: the evaluation environment is itself part of the security boundary. Across the taxonomy and records, we examine controls for containment, privilege separation, provenance, and responder access, including the dual-use problem that defensive artifacts may also enable misuse. The review identifies practical priorities for evaluating cyber capability together with the security of the environment in which that capability is exercised.

arXiv

Lifted State Hypothesis in Large Language Models

Bumjin Park, Jaesik Choi

Large language models (LLMs) adapt rapidly through fine-tuning and in-context learning, yet it remains unclear which inputs they treat as the same case and why their predictions change together. We introduce the Lifted State Hypothesis. Under fixed model parameters, context scope, and target computation, samples indistinguishable in their observed computation-relevant behavior form a computation-relative type. We hypothesize that compatible episodes activate a reusable latent component---a lifted state---that supports the target computation. State reuse enables type-level generalization but creates a non-monotonic revision problem. When later evidence distinguishes a subtype, revising a state still shared with its parent may affect members whose predictions should remain unchanged. The model must separate the subtype through rerouting, a new state, or input-specific compensation. We formalize this relation between generalization and revision. We introduce the NMR-Type Dataset to evaluate LLMs. The dataset first supports a broad modulo rule. It then provides conflicting supervision for a withheld subtype while replaying earlier examples. Across full fine-tuning, LoRA, and in-context learning, models often generalize the broad rule to the subtype but fail to localize its later revision. These results provide behavioral evidence consistent with the hypothesis and motivate further study of lifted-state formation and revision.

arXiv

Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions

Zachary Izzo

In this paper, we study the connection between an LLM's output distribution and the data used to train it. Specifically, we study the degree to which an LLM's next-token distribution agrees with the empirical next-token distribution (ENTD) given the context in the training data. The ENTD is an appealing target because it is the unrestricted global minimizer of the next-token cross entropy loss used for pretraining, as well as an easily interpretable function of the pretraining corpus. We find that for a significant fraction of inputs, the LLM's distribution agrees with the ENTD almost perfectly, and the agreement generally increases with model scale and training compute. Nevertheless, there is a long tail of input sequences where the LLM and ENTD differ significantly, and we examine several possible sources of this discrepancy across the transformer architecture, training procedure, and finite-sample noise in the ENTD estimate itself. More broadly, we hope our findings will encourage more work on ``data-centric mechanistic interpretability,'' a complement to standard mechanistic interpretability that opens the black box of how model behaviors arise from the data, rather than how they are encoded in the learned weights.

arXiv

Trust but Verify:Evidence-Linked Multi-Agent Clinical Information Extraction in Pathology

Yufan Wang, Anit Kumar Sahu, Yan Fei Ng, Daniel Kang, Shayan Vassef, Soorya Ram Shimgekar, Koustuv Saha, Piyum Zonooz, Navin Kumar, Chee Leong Cheng, Li Yan Khor

Clinical feature extraction from pathology reports is challenging because relevant evidence may be distributed across coded and narrative fields and depend on specimen attribution, negation, ancillary findings, and diagnostic context. We retrospectively evaluated the NimbleMind Multi-Agent System (nMAS), a configurable workflow that separates clinician-defined field specifications from extraction models and returns report-level predictions with source-linked evidence. The study included 54 dummy gastric biopsy pathology reports from Singapore and four binary target fields, yielding 216 feature-case decisions. nMAS correctly classified 213 of 216 decisions (98.61\%), and all evidence spans associated with correct predictions occurred verbatim in the corresponding source reports. All three errors occurred in the two context-dependent \textit{H. pylori}-related fields requiring negation handling or diagnostic attribution. A single-model UMA-style comparator produced the similar label-level performance and error pattern. These findings do not demonstrate predictive superiority for the multi-agent architecture.Rather, the contribution of nMAS lies in workflow integration and traceability through configurable field specifications, complexity-based routing, report-level aggregation, and source-text validation within a clinician-reviewable workflow. Larger multi-institutional studies should assess generalizability, semantic evidence quality, adaptation effort, and clinician verification time.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.