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

One Model, Many Graphs: Learning over Attributed Graphs across Heterogeneous Modalities with Vision-Language Models

Jiayi Yang, Yifang Chen, Yuanfu Sun, Jiajin Liu, Qiaoyu Tan

Vision-language models (VLMs) provide a unified representation space for textual and visual information, yet their potential as general-purpose backbones for graph-structured data remains largely unexplored. In practice, attributed graphs exhibit substantial modality heterogeneity: some graphs contain only textual node attributes, others only visual attributes, while still others provide both. Existing graph learning approaches are typically designed for fixed modality schemas, requiring separate models for different settings and limiting scalability and cross-graph generalization. To bridge this gap, we present OMG-VLM (One Model, Many Graphs with Vision-Language Models), a unified framework for learning over attributed graphs across heterogeneous modality schemas. OMG-VLM leverages a pretrained VLM as a shared backbone and introduces structure-aware graph adapters that integrate neighborhood information while remaining compatible with the VLM's native embedding space. This design enables effective learning over text-attributed, image-attributed, and multi-attributed graphs within a single model. Extensive experiments across diverse domains show that OMG-VLM consistently outperforms state-of-the-art GNN- and LLM-based baselines on attributed graph learning tasks such as node classification and link prediction, while exhibiting strong generalization to unseen graphs and varying modality schemas. The source code is available at https://github.com/Jo-eyang/OMG-VLM.

arXiv

Parallel Noising in Neural Markov Logic Networks

Peter Jung, Giuseppe Marra, Ondrej Kuzelka

Neural Markov Logic Networks (NMLNs) are a flexible neurosymbolic relational model. Previous work has shown that, although NMLNs achieve strong performance as generative models for small relational structures, they underperform diffusion-based generative graph models on larger structures. In this paper, we strengthen NMLNs along two main dimensions: (i) we increase the expressive capacity of their potential functions using graph neural networks, and (ii) we develop a new training and inference algorithm inspired by parallel-tempering Markov chain Monte Carlo methods, which we name parallel noising. Together, these enhancements enable NMLNs to attain strong performance in graph generation relative to general diffusion-based generative graph models. Furthermore, they allow NMLNs to match the performance of specialized text-based recurrent models when generating small molecular structures.

arXiv

Data Leakage Prevention in Agentic Applications via Preemptive Hardening

Akansha Shukla, Emily Bellov, Parth Atulbhai Gandhi, Yuval Elovici, Asaf Shabtai

Agentic systems integrate LLM driven planning with interfaces to external tools, making data leakage and tool misuse feasible via instruction/data boundary failures and prompt injection attacks. Enforcing required controls consistently is particularly challenging in workflows spanning many codebases and heterogeneous agents. To address this challenge in multi agentic systems, we present a pre-deployment pipeline for scanning, hardening, and validation of agentic applications. The pipeline analyzes prompt templates, tool interfaces, and tool-invocation code to identify leakage-enabling patterns and generate actionable patches. The hardened application is then validated through adversarial prompt injection attacks and benign input variations ensuring that mitigations do not disrupt intended behavior. In the hardening stage, high-risk tools are prioritized, and minimally invasive mitigations are applied, including schema tightening, boundary sanitization, allowlist-based tool gating, and least-privilege checks. In the validation stage, the pipeline automatically generates attack inputs that mimic jailbreaks, instruction overrides, and tool-targeted manipulation, along with benign task variants, to confirm that the functionality of the hardened application is preserved after remediation. We evaluated the pipeline on five real-world agentic applications, as well as on the AgentDojo benchmark. Across all applications, the proposed pipeline identified recurring leakage-enabling patterns and generated patches that can be integrated without disrupting the intended application behavior. The resulting modifications of application code were shown to eliminate leaks when targeted by basic jailbreak and instruction-override attacks, achieving a 100% reduction in leakage, and reduce leaks by 91% under conditions of stress-induced manipulation, without the need of continuous runtime policy enforcement.

arXiv

Evaluating medical AI under missing information: same-provider judges and human raters change apparent safety

Koyar Afrasyab

Readiness stress-testing of medical AI has focused on closed-ended and multimodal benchmarks. We extend it to open-ended clinical conversation under missing information, where safe behavior means recognizing absent information and qualifying, clarifying, or not over-committing - and where the evaluator becomes part of the measurement. We stress-test four models - three flagships (Claude Opus 4.8, GPT-5.5, Grok 4.3) and one mid-tier model (Gemini 3.5 Flash) - by deleting the latter half of the final user turn in HealthBench conversations, grading responses with a four-provider LLM-judge panel and a blinded clinician-anchored reference. Two evaluator-facing results are robust. First, judge choice materially changes apparent safety: inter-judge agreement is only moderate (Fleiss' kappa = 0.65), and after adjusting for each judge's general leniency (vote-level logistic regression), a positive same-provider association remains (exact permutation p = 0.04; GPT-5.5 ~ +0.10 on the probability scale) - large enough to change which model appears to over-commit least once its own-provider judge is excluded. Second, LLM judges are more permissive than clinicians on a blinded 50-item subsample: all four are significantly more lenient than the stricter independent clinician (crediting appropriate uncertainty on 66-84% of items vs 52%), and three of four than the author-influenced consensus (Grok directional only; judge-vs-consensus kappa = 0.20-0.43). On the author-audited clinical-underdetermined subset the permissiveness gap widened and the point-estimate model ordering held. A closed-ended MedQA anchor confirms accuracy is high and option-order effects are within a +/-5-point equivalence region for three of four models, so the safety gap is about calibration, not knowledge. We release the harness, prompts, per-item outputs, judge panel, perturbation audit, and human-annotation protocol.

arXiv

Cross-Agent Campaign Attribution: Linking Asynchronous Attacks Across LLM Agents

SangJin Park, Myungsub Choi, Jineok Kim, Minseung Kang

LLM-agent defenses are typically evaluated one session at a time. In deployment, however, attacks can be distributed across independent agents, teams, and runtimes, leaving each local guardrail with only a sparse fragment. We formalize cross-agent asynchronous campaign attribution: linking sessions from the same latent adversarial campaign without shared runtime state, test-time campaign labels, or attacker identity oracles. We introduce Asynchronous Attribution Fingerprint Vectors ($A^2FV$), a lightweight proxy-side reference protocol for scoring pairwise campaign similarity from proxy-observable tool-use, timing, and prompt residue. We also construct SCD-v1, a controlled persona-matched benchmark with benign traffic, isolated attacks, multi-session campaigns, matched non-oracle evasion, and leakage audits. On SCD-v1, $A^2FV$ achieves 0.82 pairwise AUC for campaign linking, while score-only adaptations of per-session detectors and chunked LLM judges remain near chance under the same task. The strongest fixed signal is carried by structural and stylometric residue, while timing is retained as a diagnostic channel for richer proxy traces. Crossed-style controls show that the signal is partly style-sensitive but not reducible to style alone. Static and dimension-aware non-oracle stress tests further show that pairwise separability persists under controlled evasion. These results establish cross-agent campaign attribution as a distinct evaluation layer for securing LLM agents in the wild.

arXiv

AgentTrails: Towards Trust and Reuse for Agentic Tasks

Eden Wu, Sonia Castelo, Yurong Liu, Cláudio T. Silva, Juliana Freire

LLM-powered agents increasingly tackle complex tasks by invoking tools, querying databases, executing code, and manipulating intermediate artifacts. These agents follow trajectories that are typically stored as chronological logs, obscuring the underlying dataflow -- the dependencies between their actions and the artifacts they create and manipulate. This limits developers' ability to understand the agents' trails, compare executions, debug failures, and re-use the computations. We present AgentTrails, a prototype system for agent provenance and sensemaking. AgentTrails converts raw trajectories into structured provenance graphs, where tool calls are modeled as computational actions and inputs and outputs as data artifacts. The system supports the comparison of executions by placing multiple provenance graphs on a shared canvas and constructing a joined quotient graph that aligns recurring tools, artifacts, and dependency structures across trajectories. On top of this representation, AgentTrails supports pattern extraction, downstream analysis, and skill abstraction. We demonstrate AgentTrails on real-world agent trajectories, showing that it reveals hidden dependencies, aligns divergent executions, and surfaces recurring tool-use patterns beyond chronological logs.

arXiv

Predicting Activities in Aqueous Electrolyte Solutions with Hybrid Machine Learning

Zeno Romero, Maximilian Kohns, Fabian Jirasek

Activities in aqueous electrolyte solutions, usually described by ionic activity and osmotic coefficients, are important properties for modeling many processes in industry and nature. Established activity models, such as those of Pitzer or Bromley, require fitting to experimental data for each electrolyte of interest and thus cannot predict properties for unstudied systems. While some predictive approaches exist, they are typically limited in scope and rely on additional ion-specific descriptors. In this work, we introduce a new hybrid model that combines the physics-based Bromley model with a matrix completion method (MCM) from machine learning. The MCM is employed to predict the electrolyte-specific parameters of the Bromley model, exploiting the fact that these parameters can be arranged in a matrix with cations and anions as rows and columns, respectively. Due to the lack of experimental data for many electrolytes, the initial parameter matrix is sparsely populated, making the prediction of the Bromley parameters for unstudied electrolytes a matrix completion problem. The hybrid model, Bromley-MCM, was trained end-to-end on experimental data for mean ionic activity coefficients and osmotic coefficients of aqueous solutions of 478 electrolytes at 298 K from the Dortmund Data Bank. As output, we obtain a completed matrix of Bromley parameters for 83 cations and 112 anions, enabling consistent prediction of concentration-dependent activities in aqueous solutions of 9,296 electrolytes at 298~K. This substantially extends the applicability of the Bromley model while maintaining high predictive accuracy, as demonstrated through evaluations on electrolytes excluded from model training.

arXiv

An unsupervised clustering analysis of breast cancer data derived from electronic health records enhanced through UMAP dimensionality reduction

Davide Chicco, Nicoletta Benvenuto

Breast cancer is one of the most widespread types of cancer, affecting approximately 8 million women worldwide. Electronic health records of patients diagnosed with this disease can serve as valuable datasets for computational analyses, enabling the discovery of new insights about the pathology. Unsupervised clustering, in particular, can identify groups of patients with medically significant features, revealing data trends that might otherwise go unnoticed by medical doctors. In this study, we first applied the DBSCAN density-based clustering method to three independent datasets derived from electronic medical records of patients with mammary carcinoma. Subsequently, to enhance our results, we preceded the DBSCAN application with a dimensionality reduction phase using UMAP. We evaluated our clustering outcomes using three statistical indices (DBCV, DCSI, and DISCO). Our results confirm the effectiveness of combining UMAP with DBSCAN for clustering data derived from electronic health records, paving the way for the medical interpretation of the patient groups identified by our approach.

arXiv

Deep learning-based prediction of time-resolved adhesive forces in viscoelastic Hertzian contacts

Ali Maghami, Merten Stender, Michele Ciavarella, Antonio Papangelo

Fast prediction of the response of adhesive soft viscoelastic contacts represents a current challenge in soft robotics and for gripping and manipulation tasks. Determining the complete time-resolved force trajectory requires full numerical simulations, whose computational cost is strongly parameter-dependent, making them impractical for real-time application or design-optimization loops. In this work, we overcome this limitation by training a scalar-conditioned, stateful, sequence-to-sequence deep learning model to predict the full force evolution from a prescribed displacement history for both short- and long-range adhesion regimes. The data set spans four orders of magnitude in loading and unloading rates and includes varied dwell times, with the Tabor parameter ranging from $0.2$ to $3.2$. To enable learning across these heterogeneous time scales, we introduce a fixed-measurement-step (FMS) representation that converts variable-length trajectories into fixed-length sequences while preserving their physical-time information. Different architectures were trained, including long short-term memory (LSTM) networks, temporal convolutional neural (TCN) networks, and time-distributed dense layers with three different Tabor-conditioning mechanisms. The models were compared using global waveform and error metrics. We found that the best-performing model has an LSTM architecture with concatenated conditioning, which achieves a held-out mean-squared error of $5.0\times10^{-4}$, a median pull-off-force error of $\approx2.2\%$, and a median hysteresis error of $\approx1.1\%$. For the held-out protocols, the model predicts a complete force trajectory with a median inference time of $0.16$ s. The model is tested across unseen parameter combinations and against analytical limiting cases, providing a rapid surrogate for repeated numerical evaluations with potential use in control-oriented applications.

arXiv

Adopting Reinforcement Learning with Verifiable Rewards for Molecular Generation

Mingxuan Ouyang, Hao Lan, Wanyu Lin

Leveraging large language models (LLMs) for molecular generation has shown remarkable potential in chemical and drug design. Current methods primarily rely on supervised training or fine-tuning with limited datasets, which are insufficient to capture complex molecular design objectives. While some approaches attempt to guide generation toward specific goals, they often lack direct optimization mechanisms, making it difficult to align generated molecules with desired properties. To tackle these challenges, we propose \textbf{LLMol}, a principled reinforcement learning framework that directly incorporates verifiable rewards for targeted molecule generation. The key insight is to formulate molecular design as a goal-conditioned sequence prediction task, where verifiable rewards serve as explicit supervision to drive generation toward desired objectives. LLMol follows a two-stage training paradigm combining supervised learning and reinforcement learning. In the first stage, large language models are supervised fine-tuned to capture chemical syntax and molecular distributions. In the second stage, we introduce Reinforcement Learning with Verifiable Rewards (RLVR), which directly integrates property-based reward signals to guide molecular generation toward task-specific objectives. To address the high variance and instability common in discrete sequence optimization, we adopt Group Relative Policy Optimization (GRPO), a stable on-policy algorithm that smooths reward signals and improves training robustness. This framework enables LLMol to effectively handle a range of molecular design tasks, including single-property targeting (e.g., penalized logP, QED) and structure-constrained optimization. Experimental results demonstrate that LLMol consistently outperforms existing methods, achieving higher success rates and improved efficiency across diverse molecular benchmarks.

arXiv

Spectral Higher-Order Neural Networks Have Sharp Expressivity Bounds

Gianluca Peri, Diego Febbe, Duccio Fanelli

Neural hypergraphs are a natural generalization of neural networks, the reference models in modern machine learning. Yet, their deployment has proven demanding: the number of weighted hyperedges required leads to an intractable parameter explosion. However, a novel parametrization that leverages spectral attributes for neural hypergraphs has been recently proposed, that enables to recycle parameters via a weight sharing scheme and consequently yields a significant reduction of the associated computational cost. Preliminary tests carried out on spectral higher-order architectures pointed to meaningful improvements in both performance and interpretability. Building on these results, we advance the benchmarking efforts by evaluating the spectral higher order framework on N-bit parity tasks, a well-established testbed known to be particularly challenging. As we will convincingly argue, Spectral Higher-Order Neural Networks (SHONNs) possess a versatile and highly tunable hypothesis space.

arXiv

One Rewrite to Fix Them All? Type-Aware Repair Allocation for Text-to-Image Prompt Optimization

Haoyue Liu, Xiaoyu Ma, Ye Chen, Shuguang Cui, Xiaoying Tang

Text-to-image (T2I) generators often fail to follow their prompts faithfully, producing wrong counts, swapped attributes, ambiguous relations, and illegible text. Prompt optimization repairs such failures by rewriting the user prompt, requiring no generator retraining, and has yielded promising results. However, existing optimizers absorb heterogeneous failures into one uniform prompt expansion, even though each calls for different repair language. We formulate semantic prompt optimization as atomic repair allocation: each failed proposition is routed to a type-conditioned repair operator before the resulting local constraints are compiled into one executable prompt. We instantiate this formulation in the training-free Type-Aware Repair Allocation (TARA) framework, which separates diagnosis, allocation, compilation, and a semantic repair gate, an accept-or-revert controller over exactly one prescribed repair that prevents semantic regressions. Extensive experiments on DSG and TIFA across four frozen generators demonstrate that TARA achieves the best semantic accuracy in all eight benchmark-generator cells, improving over VisualPrompter by 5.6 and 2.6 points on DSG and TIFA, respectively, while maintaining image quality and running fastest in our matched local setting at 16.0 seconds versus 20.0 seconds per prompt.

arXiv

Unsupervised Multi-kernel Learning for Automated Algorithm Selection

Yihang Lu, Tome Eftimov, Carola Doerr

Automated algorithm selection in black-box optimization typically relies on supervised models that map landscape features to algorithm performance labels. Such models are costly to train, benchmark-dependent, and often fail to generalize to unseen problem classes. We study an unsupervised alternative: multi-kernel clustering over heterogeneous landscape representations, in which problem instances are grouped without using performance labels in the clustering stage, and the resulting clusters are mapped post hoc to solver recommendations through a strictly separated three-stage evaluation protocol. Drawing on two decades of advances in multiple kernel learning, we adopt a multi-kernel k-means formulation that jointly learns cluster assignments and kernel weights over four heterogeneous landscape views: ELA, DeepELA, DoE2Vec, and TransOptAS. On affine BBOB-derived selector tasks for Differential Evolution (DE) and Particle Swarm Optimization (PSO) at a fixed evaluation budget, we report mean plus or minus standard deviation selector profiles over 50 independent random seeds for stochastic configurations. Multi-kernel clustering obtains the strongest mean profile on the DE portfolio and remains competitive with, and nominally ahead of, the leading baselines on the more compressed PSO portfolio, where differences among the best methods are small relative to stochastic variation. In representative median-seed runs used for visualization, the learned kernel weights retain ELA and TransOptAS while assigning zero weight to DeepELA and DoE2Vec, providing a task-specific interpretation of which representations are retained by the multi-kernel model for selector-oriented grouping.

arXiv

Biological Amnesia in ICU Time-Series Prediction: A Drift-Adaptive Two-Stream Architecture with Temporal Retrieval

Fatema Ferdous Tamanna, K. M. Merajul Arefin, Md. Abdul Masud

Background: Clinical decision support systems degrade silently as treatment protocols evolve, yet standard adaptation methods treat models as monolithic blocks, unable to distinguish stable patient physiology from shifting institutional practice. Methods: We propose an adaptive clinical intelligence architecture for ICU intervention prediction that structurally decouples physiological from treatment representations, confining parameter updates to the treatment stream upon a dual distributional and accuracy trigger. Automated audit logs record which treatment features drove each adaptation event and how their importance shifted. At inference, an attribution-driven Temporal RAG module grounds each prediction in patient-specific, era-matched PubMed evidence anchored to the patient's dominant physiological features. Experiments used 84,792 MIMIC-IV stays (2008-2022) under strict chronological split. Results: Drift localised entirely to the treatment stream, validating the structural prior. Selective adaptation improved vasopressor and septic shock discrimination and calibration over the static source model. A fully retrained baseline yielded marginally higher aggregate discrimination but missed 26 septic shock cases the framework correctly identified, with none in the reverse direction; retrieval consistency with the pre-adaptation source model was preserved by the framework but degraded substantially in the retrained baseline. Conclusions: Structurally constraining adaptation to drifting components while preserving stable physiological representations enables clinical AI to evolve with practice without distorting learned patient biology. This architecture offers a template for governable, interpretable deployment of adaptive models in high-stakes clinical environments.

arXiv

Subject-Conditioned Glucose Forecasting in Type-1 Diabetes

Giorgia Rigamonti, Mirko Paolo Barbato, Davide Marelli, Paolo Napoletano

Accurate forecasting of blood glucose concentration is key in the management of Type 1 Diabetes, facilitating early detection of adverse glycemic events and supporting timely therapeutic interventions. Despite recent advances in glucose prediction, most existing approaches rely on population-level representations or implicit personalization strategies that fail to deliver effective subject-specific forecasts. In this work, we propose Subject-Conditioned Glucose Prediction (SCGP), a novel multimodal deep learning architecture conceived for personalized blood glucose prediction. SCGP conditions glucose predictions based on observed glucose data and a compact subject-specific representation learned from contextual information. By explicitly separating subject characterization from glucose dynamics modeling and avoiding early fusion of heterogeneous inputs, the proposed framework effectively captures inter-subject variability while preserving robust and reliable temporal modeling. Experiments on two state-of-the-art benchmark datasets demonstrate that SCGP consistently improves forecasting performance, enabling reliable detection of adverse glycemic events across multiple prediction horizons, highlighting the benefits of explicit subject conditioning for personalized diabetes management.

arXiv

The Tractability Landscape of Sampling with Inexact Scores

Anming Gu, Kevin Tian, Hubert Yang, Yusong Zhu

We provide a simple and tight characterization of the types of inexact score oracle access that permit sampling with vanishing total variation bias, for a standard, well-behaved target family. Our main result shows that any weaker error than the sub-Gaussian assumption used by [YW26] rules out the tractability of unbiased sampling. This strengthens the conclusion of [CCSW26] to be algorithm-agnostic, and to hold for a wider range of error assumptions.

arXiv

Strategy-Following Multi-Agent Deep Reinforcement Learning Considering Control Strategies Provided to Other Agents

Yamato Takahagi, Gentoku Nakasone, Yoshinari Motokawa, Toshiharu Sugawara

This study proposes a learning method for multi-agent systems that allows agents to be controlled through human manager instructions after learning and enables uninstructed agents to implicitly complement the overall work based on the actions of other agents. Multi-agent applications using deep learning have shown potential; thus, to achieve extensive social applications, humans should be able to control learned agents using simple methods to respond to environmental and social changes. Even without such changes, learned coordination often does not match the expectations of human managers, making it preferable to control coordination structures to match human intentions. Some studies have aimed to control agent behavior using simple instructions. However, they assumed that instructions are provided to all agents, which is time-consuming and not evident when designing a better cooperation regime. Ideally, specific agents should receive key action instructions, while others should automatically complete the remaining tasks. The proposed method, which extends previous work on controllability in multi-agent deep reinforcement learning, enables uninstructed agents to adaptively complement overlooked tasks and areas. The experimental results show that agents using the proposed method can shift to another cooperative structure and achieve better performance than those using conventional methods.

arXiv

DWM: Separating World Effects from Actions in Latent World Models

Yi-Ge Zhang, Tianqi Du, Qi Zhang, Yisen Wang

Latent world models underpin much of modern model-based control, yet current action-conditioned formulations supervise the next-latent transition with a single, undifferentiated target, forcing a monolithic learning signal to absorb every source of state change. In real world, however, transitions arise from two heterogeneous sources: an action-driven component induced by the agent, and an action-invariant world effect -- the change that would still occur under a null action, dictated by the environment's intrinsic dynamics (e.g., gravity-driven sliding, inertia, contact rebound, and persistent drift). Fusing them into a single target entangles the two inside the latent transition, prevents the model from attributing observed changes to their underlying causes, and undermines the transferability of the learned dynamics. We introduce DWM (Decomposed World Model), a supervision-level framework that operationalizes this decomposition. DWM augments the predictor of a latent world model with an auxiliary world head, regularized by a normalized world-contrastive objective to be action-invariant, while the original pred head is coupled to it via an orthogonality constraint; together, the two signals induce an explicit additive decomposition of the predicted transition into an action-invariant and a complementary action-driven component, without altering the underlying architecture or inference pipeline. To evaluate DWM under persistent world effects, we construct W-variants of three standard control benchmarks -- PushT-W, Reacher-W, and TwoRoom-W -- each instantiating a distinct action-invariant dynamic. DWM matches strong baselines on the flat counterparts and delivers a mean absolute improvement of 13.1% in CEM planning success across the W-variants.

arXiv

What the Waveform Knows: Transparent-first Speech and Audio Intelligence with Caption Studio

Cheng Siong Chin, Jianhua Zhang, Mohan Venkateshkumar

Caption Studio is a transparency-first speech and audio intelligence platform that transforms spoken audio and video into structured, searchable content through automated transcription, speaker diarization, speech analytics, signal-level audio analysis, and subtitle generation. The system is built on a FastAPI backend with a real-time dashboard and adopts a three-layer architecture comprising (i) a transcription and diarization core based on Whisper-class automatic speech recognition and pyannote speaker diarization, (ii) an audio intelligence layer that extracts acoustic and linguistic features, including waveforms, spectrograms, pitch, speaking rate, silence, filler-word frequency, and sentiment, directly from the audio signal, and (iii) an integration layer that supports data export and downstream workflow integration. A principal contribution of this work is the transparency-first framework, in which every reported metric is explicitly identified as measured, derived, or unavailable, thereby improving the traceability, interpretability, and reliability of speech analytics. The paper presents the system architecture, benchmarking methodology, explainability and uncertainty framework, and key considerations for enterprise-scale deployment.

arXiv

Do AI-Native Biotechs Need Departments? Benchmarking Company World Models for AI-Driven Drug Development

Yinan Wang

AI-native biotechnology companies are often designed by copying human biotech org charts into agent roles. We argue for a different abstraction: a Company World Model, defined as a persistent asset-to-value state representation with transition models, explicit value functions, planning, and updating across scientific, regulatory, BD, commercial, financial, and execution constraints. We introduce a dry-lab benchmark for testing whether AI-agent organizations should mimic departments or operate around such a world model. The benchmark contains 45 retrospective public-information decision cases with strict time cutoffs, hidden outcomes, common schemas, automatic scoring, and blinded pairwise judging. We compare human-org-mimic, stronger human-org-mimic-plus, AI-native asset-centric, and AI-native value-conversion architectures. The value-conversion architecture is a prompt-level approximation of a Company World Model: a Live Asset Value Record updated by Deal, Approval, Revenue, and Investment Arbiter loops. Under a success function defined by external BD, regulatory approval and launch, and revenue discipline, it achieved the highest automatic value-conversion score and was strongly preferred over the original baselines by value-specific blinded judges. Stress tests narrowed the claim: a stronger human baseline remained competitive, and a neutral judge did not show robust value-conversion dominance. Codex-only mechanistic ablations suggest that Revenue Room, Deal Room, and Approval Room carry useful work under the target objective. The central finding is objective-sensitive: departments may remain useful governance views, but the core AI-native operating primitive should be a shared, predictive asset-to-value state rather than a static human org chart. The study is dry-lab only and does not establish real-world drug success, clinical benefit, or revenue prediction accuracy.

Keep browsing

More papers from top AI conferences

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