cs.AI · 2026-07-12 · No. 51
Artificial Intelligence, 2026-07-12.
42 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
42 entries-
01
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
Yifan Zhou, Qihao Yang, Yan Li, Donggang Li, Xiru Hu, Hokin Deng, Ziyang Gong, Xuanyi Zhou, Huacan Wang, Xiangchao...
cs.AI
Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benchmarks still say little about whether AI systems can follow this inheritance structure. We present IdeaGene-Bench (IG-Bench), a benchmark for scientific lineage reasoning and lineage-grounded idea generation. IG-Bench is organized around the IdeaGene framework: each...
-
02
Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive Analysis
Kristina Schaaff, Quintus Stierstorfer, Valerie Heckel
cs.AI · cs.HC
In this study, we present a large-scale descriptive analysis of the use of an AI-based learning assistant (Syntea) in higher education. Based on objective log data from 77,543 students enrolled in distance studies, we examine usage patterns across gender, age group, study cluster, degree, and study mode. To date, existing research on educational chatbots has largely relied on comparatively small samples and self-reported survey data, while...
-
03
AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding
Siddharth Damodharan, Radhika Gupta, Ali Alshami, Ryan Rabinowitz, Jugal Kalita
cs.AI · cs.CV
Recent advances in Vision-Language Models, Large Language Models, and Multimodal Large Language Models have improved autonomous driving tasks such as scene understanding, decision making, trajectory prediction, and visual question answering. However, evaluating whether these models can reliably reason about safety-critical incidents remains challenging. To address this gap, we present AUTOPILOT-VQA, an incident-centric visual question...
-
04
Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows
Emanuele Quinto, Carlo Andrea Rozzi, Francesco Zanitti
cs.AI · cs.PL · cs.SE
Large language model (LLM) applications increasingly use explicit workflows for tool use, retrieval, branching, checkpointing, and human approval. Existing workflow systems already address many execution concerns. This paper proposes a Lisp-inspired but language-independent conceptual model: symbolic forms, object identity, and live-image thinking are used as explanatory lenses, not implementation commitments. In this model, workflow...
-
05
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
Baha Rababah, Cuneyt Gurcan Akcora, Carson K. Leung
cs.AI
Post-training quantization is widely used to deploy large language models in resource-constrained settings, yet its evaluation relies almost exclusively on accuracy and perplexity. We show that these metrics fail to capture behavioral changes induced by quantization. We introduce correctness agreement, a decision-level metric that measures overlap in correct predictions between a base model and its quantized variants, independent of absolute...
-
06
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
Yifan Wu, Lizhu Zhang, Yuhang Zhou, Mingyi Wang, Bo Peng, Serena Li, Xiangjun Fan, Zhuokai Zhao
cs.AI · cs.CL
In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgoals can be buried in the context window or pushed beyond it, failing to influence decisions when needed. We call this failure mode "behavioral state decay". We study memory as an active intervention...
-
07
SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets
Shilin Ou, Yifan Xu, Luyao Zhang
cs.AI
As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustworthiness. In decentralized energy markets, autonomous agents may improve market utility, but may also exploit invalid physical data, create artificial liquidity, and produce unstable governance decisions. Therefore, we propose SolarChain-Eval, a physics-constrained benchmark for evaluating...
-
08
Formal Mechanisms for Market Stability in Self-Interested Agent Societies: A Marketplace Simulation Study
Eugene Ng Yi Sheng, Bingquan Shen
cs.AI
Self-interested agents, left unconstrained, tend toward defection in repeated social dilemmas, causing cooperative gains from trade to collapse. This paper investigates what formal mechanisms, layered on top of unrestricted communication, are sufficient for a society of such agents to maintain market stability, and how resilient those mechanisms are to adversarial attack. We instantiate the research question as a multi-agent marketplace...
-
09
The complexities of patient-centred conversational artificial intelligence
João Matos, Olivia Buege, Donny Cheung, Gary S. Collins, Paula Dhiman, Nan Li, Bingyu Mao, Benjamin W. Nelson,...
cs.AI · cs.CL
Consumer-facing health chatbots powered by large language models (LLMs) are increasingly used for symptom assessment. However, chatbot development and evaluation often rely on cooperative, articulate, simulated patients. We analysed 2,053 real patient-chatbot conversations and found that communication patterns and expression of emotions vary widely across users. We developed a patient simulator that separately models clinical content,...
-
10
Towards Precision Therapy in Hepatocellular Carcinoma: A Clinical-Reasoning LLM for Risk Stratification and Treatment Guidance
Peng Cui, Jitao Wang, Siyan Xue, Yao Huang, Haoming Xia, Dong Li, Dengxiang Liu, Weilin Wang, Liping Liu, Leida...
cs.AI
Hepatocellular carcinoma (HCC) is a common malignancy and a leading cause of cancer-related mortality. Current guidelines and staging systems provide coarse categories, but often miss within-stage heterogeneity and the clinical context in electronic medical records (EMRs). We present HCC-STAR (Hepatocellular Carcinoma Staging, Treatment And pRognosis), a clinically aligned large language model that reads routine EMR narratives and jointly...
-
11
SHAP-Weighted Cross-Modal Expert Fusion for Emotion and Sentiment Recognition: Evidence and Limits
Adis Alihodzic, Selma Skopljakovic Hubljar
cs.AI
Multimodal emotion and sentiment recognition is commonly addressed by early fusion, which concatenates modalities before classification, or late fusion, which combines independently trained unimodal predictors. Early fusion can be accurate but monolithic, while late fusion is modular but may lose cross-modal interactions. This paper revisits XAI-guided adaptive fusion (\xgaf), a tree-based mixture of unimodal and cross-modal experts whose...
-
12
CommuniWave:A Machine Learning Model for Quantifying the Degree of Temporary Informal Behavior in Urban Communities
Hongye Yang, Shien Liu, Zhihao Xie
cs.AI
For urban managers and designers, improving the functional attributes of urban communities to enhance territorial resilience in the face of complexity and uncertainty is crucial. Currently, community planning often follows a top-down approach and lacks effective metrics to quantify informal behaviors of residents, leading to frequent conflicts with original plans. This study introduces CommuniWave, a machine learning model designed to...
-
13
AI-guided stimuli discovery and generation to optimize facial emotion perception studies in autism
Kushin Mukherjee, Na Yeon Kim, Maren Wehrheim, Ralph Adolphs, Kohitij Kar
cs.AI · cs.LG
Understanding perceptual differences between autistic and neurotypical adults requires behavioral assays that are sensitive, reliable, and mechanistically informative. Facial emotion perception is a useful test case because group differences have been reported, but findings vary across studies. Here we show that this variability may reflect image-level sparsity: autistic-neurotypical differences in emotion judgments were concentrated in a...
-
14
Drift-Aware Temporal Graph Rewiring (DATGR) for Adaptive Semantic Modeling in Biomedical Text
Bharathwaj Vijayakumar, Sahana K. Varadaraju
cs.AI
Biomedical language evolves rapidly as new discoveries emerge, causing traditional text models to lose semantic fidelity over time. Static embeddings and co-occurrence graphs cannot capture such evolution, leading to performance degradation in retrieval and knowledge discovery tasks. This paper introduces a Drift-Aware Temporal Graph Rewiring (DATGR) framework that models concept evolution by dynamically updating co-occurrence edges based on...
-
15
Applying JEPA-Style Predictive Learning to JA4-Derived Network Fingerprints
Javier Izquierdo, Aygul Zagidullina
cs.AI
I-JEPA and V-JEPA learn by matching latent predictions to target encoder outputs rather than regenerating the original input, and this has worked well for images and video. We explore whether the same objective works for compact network fingerprints. We built JA4-JEPA, a Transformer-based model trained on JA4, JA4H, JA4S, and JA4X subfields drawn from JA4DB and CIC-IDS- 2017. The training data combines roughly 397K samples from both sources,...
-
16
OmniFood-Bench: Evaluating VLMs for Nutrient Reasoning and Personalized Health Advice
Qian Jiang, Zhecheng Shi, Jingpu Yang, Zirui Song, Miao Fang
cs.AI
The rapid integration of Large Vision-Language Models (VLMs) into critical infrastructure promises to revolutionize personalized healthcare and dietary management. However, in the domain of food systems, autonomous agents face a unique and persistent challenge: the "Systemic Information Asymmetry" between visual appearance and intrinsic nutritional composition. Existing benchmarks primarily focus on coarse-grained classification tasks, such...
-
17
Game Theory Driven Multi-Agent Framework Mitigates Language Model Hallucination
Runzhe Liu, Biquan Bie, Zihao Wang, Yuchao Ma, Yexin Liu, Xinghai Li, Harry Yang, Wenbo Yang, Jinzhe Cao, Shengyang Tao
cs.AI
The application of lightweight Large Language Models in rule-based scientific domains remains severely limited by their tendency to mimic linguistic patterns rather than reproduce axiomatic reasoning, causing frequent hallucinations. Here, we show that G-Frame, an adaptive multi-agent framework integrating Bayesian and team game principles, establishes an automated closed-loop for high-quality data synthesis and model training. By forcing the...
-
18
Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning
Lu Dai, Ziyang Rao, Yili Wang, Hanqing Wang, Hao Liu, Hui Xiong
cs.AI · cs.CL
Fine-tuning LLMs to inject new knowledge faces a critical challenge: LLMs can quickly memorize new facts, yet fail to use them for downstream reasoning tasks. We formalize this failure as the \textit{\textbf{Knowing--Using Gap}}, characterized by an accuracy gap and a temporal lag between memorization and generalization. To understand this phenomenon, we fine-tune LLMs with unseen knowledge and monitor the spatial permeation dynamics of the...
-
19
FedOPAL: One-Shot Federated Learning via Analytic Visual Prompt Tuning
Lingyu Qiu, Daniela Annunziata, Stefano Izzo, Fabio Giampaolo, Francesco Piccialli
cs.AI
With the widespread deployment of basic models in edge intelligence, communication bandwidth has become a core bottleneck restricting the scalability of federated learning. Although one-shot federated learning alleviates this problem by minimizing communication rounds, existing iterative fine-tuning or knowledge distillation methods still face challenges such as high server-side computational costs and hyperparameter sensitivity. Analytical...
-
20
MobiDiff: Semantic-Aware Multi-Channel Discrete Diffusion for Human Mobility Data Generation
Rongchao Xu, Lin Jiang, Dahai Yu, Ximiao Li, Taichi Liu, Desheng Zhang, Yuan Tian, Guang Wang
cs.AI
Human mobility data are essential for transportation optimization, urban planning, and resource allocation, yet real-world mobility data are costly to collect and difficult to share due to privacy concerns. Recent diffusion-based methods have shown promise in synthesizing realistic mobility patterns, but they typically rely on continuous or latent spatio-temporal traces, limiting their ability to natively model discrete semantic events with...
-
21
Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models
Matteo Santelmo, Xiuying Wei, Israa Fakih, Felix Bauer, Juan Garcia Giraldo, Chengkun Li, Etienne Bamas, Emmanuel Abbé
cs.AI
Modern AI models achieve strong performance on many established benchmarks, yet they still fail on tasks that humans find almost trivial, such as manipulating a string or drawing a dog with five legs. These examples suggest that existing benchmarks may under-measure persistent blind spots in current systems. We introduce $\texttt{blind-spots-bench}$, a benchmark designed to expose such blind spots through tasks that appear simple for humans...
-
22
INTENT: An LSTM Framework for Vehicle Intention Prediction in Intersection Scenarios with Comprehensive Ablation Analysis
Logine M. Zaki, Catherine M. Elias
cs.AI · cs.LG · cs.RO
Vehicle intention prediction is a pivotal aspect in the agility and safety of autonomous vehicles in all driving scenarios; if genuine enhancement of autonomous vehicles are required, we need to make them adopt human interpretation of driver's intention especially in cases that require a lot of human interaction as well as complex driving behaviors like the ones at intersections, roundabouts and emergency cases such as sudden stops where...
-
23
Psychological Competence as a Missing Dimension in AI Evaluation
Marcos Economides, Paul M. Sacher, Samuel Salzer, Alexis Michelle Abellar, Fendi Tsim, Antoine Ferrère
cs.AI
Current AI evaluation frameworks focus primarily on technical performance, including accuracy, robustness, reasoning ability, and policy compliance. These measures remain essential, but they are not sufficient for systems that interact directly with users through natural language. Human-facing AI systems are increasingly used as advisors, coaches, tutors, and companions. In these roles, their responses can shape how users reason, interpret...
-
24
Understanding Axes of Difficulty For Long Context Tasks Via PredicateLongBench
Siddhartha Jain, Ameya Velingker
cs.AI
Large language models (LLMs) have demonstrated rapidly improving long-context capabilities, prompting a wave of benchmarks designed to evaluate them. However, existing long-context evaluations - from Needle-in-a-Haystack (NIAH) tests to more recent multi-hop reasoning and summarization tasks - predominantly measure average-case performance, and many are either saturated or lack robustness. Notably absent is a systematic way to probe how...
-
25
PolyUQuest: Verifiable Structure-Aware Web RAG over Heterogeneous Graphs
Ying Liu, Yi Ye, Quanyu Feng, Mingxi Ye, Mingtao Zhang, Haoyang Li, Chen Jason Zhang, Qing Li
cs.AI
Existing retrieval-augmented generation (RAG) systems treat web pages as flat text, losing the structural and semantic signals encoded in HTML. We present PolyUQuest, a verifiable, structure-aware web RAG framework built on a heterogeneous graph that unifies hyperlink topology between pages, DOM hierarchy within pages, and entity-relation knowledge across pages. A two-tier router dispatches each query to one of three retrieval modes matched...
-
26
Different Teachers, Different Capabilities: Sub-1B On-Device Distillation for Structured Text Enrichment
Vinay Kumar Chaganti
cs.AI · cs.CL
High-volume structured extraction pays a large model's latency on every item, so distilling the task into a small on-device model is attractive: comparable output at a fraction of the time and cost. We measure what that distillation actually delivers, per sub-task. Each news article is mapped to one JSON object with a short summary and five categorical labels. We distill an 8B reasoning teacher (deepseek-r1:8b) into a 0.6B student...
-
27
MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters
Yuming Yang, Xiao Sun, Yuanwei Zou, Zhengxiao Wu, Yun Chen, Jiang Zhong, Haoyang Zeng, Jingwang Huang, Kaiwen Wei
cs.AI
Large language models (LLMs) have shown strong performance on isolated psychiatric tasks, including dialogue, diagnosis, and treatment planning, yet existing benchmarks rarely simulate complete psychiatric clinical encounters. We introduce $\textbf{MentalHospital}$, a virtual evaluation environment for LLM-based psychiatric clinical encounters. MentalHospital instantiates the Subjective Interviewing, Objective Examination, Diagnostic...
-
28
Compete Then Collaborate: Frontier AI Teachers Build a Verifiable Curriculum to Improve a Coding Student Beyond Imitation
Miseong Shawn Kim
cs.AI
Large language models increasingly serve as teachers generating training data for smaller students. Prior multi-teacher knowledge distillation methods merge outputs without determining which frontier model teaches best, often relying on an LLM judge biased toward its own outputs. We introduce a compete-then-collaborate framework where four frontier AI teachers (Claude, Codex-GPT, Grok, Gemini) are ranked head-to-head by an execution-based...
-
29
AutoPersonas: A Multi-Timescale Loop Engine for Open-Ended Persona Evolution
Mengchen Li
cs.AI · cs.CL · cs.HC
Long-term persona agents must remain identifiable while adapting to new events, relationships, evidence, and social conditions. We identify self-locking as a runtime failure mode in continuing persona-life loops: locally plausible events keep appearing while the generated life collapses toward familiar environments, weak relationships, suspended decisions, and stale life stages. We trace this failure to model-level convergence toward...
-
30
Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction
Sophia Koehler, Antonia Wüst, Inga Ibs, Wasu Top Piriyakulkij, Wolfgang Stammer, Constantin Rothkopf, Kevin Ellis,...
cs.AI · cs.CV
A central challenge in building intelligent systems is enabling agents to jointly perceive complex inputs, form hypotheses about hidden patterns, and design informative experiments to test them. To study this problem, we propose ZendoWorld, a controlled interactive environment in which agents must infer a logical rule about visual game observations, acquire information by proposing new scenes, and refine their hypotheses based on feedback...
-
31
A First-Principles Theory of Slow Thinking and Active Perception
Hongkang Yang, Zhi-Qin John Xu, Feiyu Xiong, Weinan E
cs.AI · cs.CL · cs.LG
As part of a series on first-principles modeling of cognitive functions, this paper attempts to provide a mathematical formulation of thinking and perception. It formally derives slow thinking or more generally, active perception, and encompasses the design, training and inference of slow thinking large language models. Our starting point is the lifting and projection of probability distributions on the observable and latent spaces, with the...
-
32
ASMR: Agentic Schema Generation for Ship Maintenance Report Writing
Sohrab Namazi Nia, Amogh Dalal, Ning Sa, Peter Ly, Marti Zentmaier, Tomek Strzalkowski, Jay Miller, Rishi Singh,...
cs.AI · cs.MA
In this paper, we study the automatic schema generation problem: given a collection of historical ship maintenance and operational reports across multiple form categories, automatically discover compact and informative schemas that capture the essential information requirements of each report type. To address this challenge, we propose ASMR, a modular agentic framework consisting of two specialized agents. A Field Generation Agent extracts...
-
33
Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets
Jack Hopkins, Dipika Khullar, Fabien Roger
cs.AI
Black box auditing of language models is an essential pre-deployment tool, but it may miss subtle forms of misalignment and hidden information. To better elicit hidden information during an auditing process, we introduce \emph{overthinking}: the process of using reasoning task vectors to amplify the propensity to think out loud of reasoning models. Given the parameters of a non-reasoning instruct model $M$ and reasoning-distilled model $R$,...
-
34
Answer Set Programming Energised! End-to-End Neurosymbolic Reasoning and Learning with ASP and Energy Based Models
Jakob Suchan, Julius Monsen, Salim Baloch, Mehul Bhatt
cs.AI
We present a general neurosymbolic reasoning and learning methodology based on a modular integration of answer set programming with an energy based model substrate. Key contributions are: (1) supporting joint optimisation in the continuous latent space through explicit ASP-based declarative semantics fully incorporating background knowledge, constraints, non-monotonic inference; and (2) advancing recent works at the interface of answer sets,...
-
35
CausalDS: Benchmarking Causal Reasoning in Data-Science Agents
Andrej Leban, Yuekai Sun
cs.AI · cs.CL · cs.LG
Large language models (LLMs) increasingly act as integrated data-science agents, combining abstract reasoning with advanced tool use. Yet the relevant benchmark landscape largely divides into symbolic causal reasoning benchmarks without realistic data analysis or data analysis benchmarks without a principled causal data-generating structure. Furthermore, existing causal evaluation datasets are often restricted to curated examples from...
-
36
PARA-PV: Physics-Aware Retrieval-Augmented PV Prediction Based on Frozen Foundation Model and Distribution Shift Correction
Hang Fan, Weican Liu, Ying Lu, Dunnan Liu, Long Cheng, Wei Wei
cs.AI
Accurate photovoltaic (PV) power forecasting is essential for reliable grid dispatch and renewable energy integration, yet it remains challenging because PV generation is jointly shaped by weather variability, day-night transitions, regime-dependent dynamics, and strict physical constraints. We propose PARA-PV, a Physics-Aware Retrieval-Augmented framework that embeds physical knowledge throughout the forecasting process. The framework first...
-
37
Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring
Jennifer Za, Julija Bainiaksina, Nikita Ostrovsky, Tanush Chopra, Victoria Krakovna
cs.AI · cs.LG
Chain-of-thought (CoT) monitoring is a promising safety mechanism for AI agents, based on the premise that visible reasoning traces can surface misaligned or deceptive behavior. While effective in standard scenarios, recent work highlights that LLMs remain vulnerable to persuasion-based jailbreaks, where natural-language arguments override model constraints. We stress-test whether this vulnerability extends to monitoring LLMs: can an...
-
38
When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals
Kaihua Ding
cs.AI
LLM-as-judge (Zheng et al., 2023) is increasingly the default for evaluating AI systems in enterprise pipelines, often scaled to ensembles (Verga et al., 2024) or "mixture-of-experts" (Shazeer et al., 2017) panels of judges. These systems share a key assumption: that consistency -- agreement among judges, or among a model's own samples -- indicates correctness. We show this assumption is unreliable. Agreement is not accuracy: a model can...
-
39
A safety-oriented hypothetico-deductive framework for AI-assisted differential diagnosis
Fan Ma, Mauro Giuffrè, Donald Wright, Kent McCann, Mark Iscoe, Lingfei Qian, Mingyang Jiang, Chi Wing Ng, Na Hong,...
cs.AI
Diagnostic error is a major threat to patient safety, yet current large language model (LLM) systems often treat diagnosis as a one-shot prediction task, lacking safeguards against missed high-risk alternatives or rigorous verification of their reasoning. Here, we present AegisDx, a safety-oriented framework for hypothetico-deductive clinical reasoning. AegisDx coordinates specialized LLM components through role-specific contracts, structured...
-
40
From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents
Joongho Ahn, Moonsoo Kim
cs.AI · cs.CL · cs.SE
Enterprise large language model (LLM) applications often begin as prototypes whose behavior is carried by prompts and retrieval context. Productization adds requirements for source boundaries, entity routing, answer contracts, and reproducible traces. We present a harness-engineering approach that reconstructs this pattern into a traceable, auditable LLM-agent architecture: deterministic behavior moves into code, manifests, schemas, and...
-
41
Concretized Proposition Prompting Resolves Composition-Knowledge Dichotomy in Large Language Models
Changhun Lee, Minguk Jeon, Jongkyung Shin, Chiehyeon Lim
cs.AI
LLMs often struggle to balance compositionality with knowledgeability, a challenge we define as Composition-Knowledge Dichotomy. To address this, we propose Concretized Proposition Prompting (CPP), a framework that explicitly concretizes propositions relevant to questions. The results demonstrate that CPP significantly enhances reasoning performance, particularly in medical benchmarks where precise knowledge is paramount, while being...
-
42
Agentic Neural Architecture Search
Seokhoon Jeong, Mijung Kim, Taehwan Kim
cs.AI
Neural architecture search (NAS) methods have grown increasingly efficient, yet they remain bounded by manually engineered search spaces that require substantial domain expertise and must be rebuilt for every new task. Large language models (LLMs) can generate architectures in an open-ended space, but how to optimally divide the labor between LLM-driven design and NAS-driven search remains unexplored. We propose a mechanism that bridges these...
This edition is part of The Daily Abstract — cs.AI archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.