cs.AI · 2026-09-11 · No. 112
Artificial Intelligence, 2026-09-11.
64 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
64 entries-
01
Can Edge-Deployable Vision-Language Models Identify Species?
William Zhou, Mayukha Siripuram, Xiao Yan, Ziqi Liu, Yi Ding
cs.AI
Camera traps often run in the field on edge hardware with limited or no connectivity, making small, locally-deployable vision-language models (VLMs) -- not frontier-scale ones -- the practically relevant class to evaluate for species identification. We test whether models in this deployment-relevant 2--8B range carry genuine taxonomic knowledge, evaluating four such VLMs (Qwen3-VL 2B/4B/8B, Gemma3 4B) against the domain-specific specialist...
-
02
Artificial Id: Drive and Persistent Alignment in Agentic AI
Yakov Pyotr Shkolnikov
cs.AI
Agentic AI is moving from bounded task execution toward systems that retain consequential state, continue operating and adapt across task boundaries. That shift creates a control problem that current harnesses largely solve by hand: objectives, retries, verification, stopping rules and other behavioral transitions are specified externally. We propose an artificial id, an adaptive internal drive for determining whether behavior should...
-
03
MindTopo: Can Foundation Models Reason in Topological Space?
Yunfei Ge, Anbang Liu, Qineng Wang, Johnalbert Garnica, Jianwen Lyu, Zihan Wang, Reuben Tan, Jianfeng Gao, Ruohan...
cs.AI · cs.CL · cs.CV
Spatial reasoning depends not only on metric properties such as distance, angle, and shape, but also on topological relations that remain invariant under continuous deformation. Cognitive science identifies these relations as foundational to spatial understanding, yet foundation-model evaluations largely focus on metric or viewpoint-dependent relations. We introduce MindTopo, a benchmark of topological intuition across five properties...
-
04
On the Regularization Landscape for the Linear Recommendation Models
Dong Li, Zhenming Liu, Ruoming Jin, Hao Zhou, Zhi Liu, Jing Gao, Bin Ren
cs.AI
Recently, a wide range of recommendation algorithms inspired by deep learning techniques have emerged as the performance leaders on several standard recommendation benchmarks. While these algorithms were built on different DL techniques (e.g., dropouts, autoencoder), they have similar performance and even similar cost functions. This paper studies whether the models' comparable performance are sheer coincidence, or they can be unified under a...
-
05
Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models
Rodion Krjutškov, Eduard Barbu, Nikos Sakkas, Sofia Yfanti
cs.AI · cs.LG
Energy consumption forecasting relies on increasingly complex machine learning (ML) models, such as Genetic Programming-based symbolic regressors, whose predictions can be difficult for facility managers and building operators to interpret. Explainable Artificial Intelligence (XAI) techniques address this opacity, but traditional XAI dashboards require substantial technical expertise and provide limited flexibility for dynamic, context-aware...
-
06
From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge
Wenkang Wei, Yuan Fang, Renhe Jiang, Hong Cheng, Xingtong Yu
cs.AI
How does a language model's dependence on query-routing information and target knowledge change as it answers a question? We study this question through layerwise interventions on the hidden state at the end of the question. Across Qwen, Llama, and Gemma, we compare country-continent questions with noun, adjective, and code answers while keeping several fitted measurements distinct. A pair-conditioned request direction describes which country...
-
07
A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-Channel and Bias Coefficients
Suwan Wu, Yumeng Lin, Pengcheng Yuan, Xiaolong Jiang
cs.AI · cs.CL · cs.LG
Per-token gating of forward/reverse KL losses has become a standard technique for on-policy knowledge distillation (OPD), but existing methods such as EOPD (Jin et al., 2026) and ToDi (Jung et al., 2025) each fix a single gating signal and a single gating direction, and the two have never been compared directly. We introduce a four-coefficient parameterization lambda_t = sigma(a * h_t + b * u(x) + c + d * gap_t) in which direction-aligned...
-
08
SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control
Suwan Wu, Yumeng Lin, Pengcheng Yuan, Xiaolong Jiang
cs.AI · cs.CL · cs.LG
For industrial content risk control, the real deployment constraint is not average accuracy but how much risk can be auto-handled under high precision and second-level latency. We present SIRF (Spec-Internalized Risk Foundation Model), which internalizes a platform's complex policies, synthesized without additional human annotation via EntiGraph, MAGA rewriting and account-level chain-of-thought (CoT), into the weights via continued...
-
09
When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making
Ken Chen, Wei Wang, Sachith Seneviratne, Hansani Weeratunge, Saman Halgamuge
cs.AI · cs.MA
When multiple LLM agents yield conflicting answers, the decision-making process dictates whether agent diversity improves performance or merely compounds shared errors. Existing collective decision-making methods, including voting, electoral rules, and LLM judges, rely on forward reasoning: they map evidence to labels in one direction. Although these methods can combine diverse forward traces, they still aggregate estimates that share this...
-
10
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization
Pingchen Lu, Xiangyi Wang, Xiang Li, Jie Mao, Zikun Qu, Junfeng Luo, Yao Shu, Bryan Kian Hsiang Low, Zhongxiang Dai
cs.AI
Large language model (LLM) agents can benefit from reusable skills distilled from prior task experience, yet existing skill optimization methods often rely on costly execution-based evaluation and substantial task data. We introduce \textbf{COBRA-Skills}, an efficient framework that formulates skill optimization as budgeted sequential optimization over a dynamically evolving candidate space. COBRA-Skills couples contextual-bandit-guided...
-
11
Geospatial AI, Dataverse Metadata, and the Study of Place-Based Government
Danny EBanks, Devika Jain
cs.AI
Harvard Dataverse hosts over 150,000 research datasets, but the geographic information those datasets carry is entered as free text by depositors and has never been assembled into a searchable structure. We construct a knowledge graph from the repository's public data and metadata, organizing 102,650 datasets within a 215,985-node network of 528,003 edges linking datasets to keywords, publications, subjects, journals, and locations. Of those...
-
12
Autonomy, Social Norms, and Alignment: Towards a Developmental Framework for Autonomous Artificial Agents
Marica Notte, Ludovica Marinucci, Vieri Giuliano Santucci
cs.AI
In recent years, artificial intelligence has made extraordinary progress thanks to large-scale models capable of generalization and the generation of complex outputs. However, transferring this potential into embodied agents reveals a significant limitation: the most advanced systems rely on pre-existing datasets and human feedback strategies that are powerful but insufficient in dynamic or unknown contexts. To adapt, an agent must acquire...
-
13
MAPLE: Memory-Augmented Planning with Language and Evolution
Kesheng Chen, Yamin Hu, Wenjian Luo
cs.AI
Domain practitioners understand their business constraints but may lack operations-research expertise or dedicated support. LLM-based optimization agents translate natural-language requirements into models or solver programs that established optimization tools can execute. This progress makes optimization more accessible, but real-world operations are dynamic: changing demand, resources, and priorities require updates to data, constraints,...
-
14
Distributed Optimization of Modular Production Systems using Model-based Reinforcement Learning with Inverse Models
Andreas Schwung, Steve Yuwono, Sofiene Lassoued, Dorothea Schwung
cs.AI · cs.LG · eess.SY
This paper presents a novel approach for data-driven self-learning control of highly flexible, modular manufacturing systems. Specifically, we employ a novel framework for model-based reinforcement learning which introduces approximate inverse process models within the training of reinforcement policies. This approach disentangles the learning of actuation dynamics and the dynamics in state space, resulting in RL-based training solely within...
-
15
Making Alternative Data Work: Context-Augmented LLMs for Financial Forecasting
Jihoon Kwon, Lawrence Liu, Daekyung Park, Sumin Kim, Haverty Jack, Hoyoung Lee, Katherine Bjorkman, Josh McKenney,...
cs.AI
When forecasting a firm's future financial performance, alternative data - data collected from non-traditional sources such as consumer transactions, web traffic, and prediction markets - can provide timely signals about firms' operating activities and broader market conditions. These signals may reveal information that is not captured by traditional public sources and can therefore provide complementary information for forecasting firms'...
-
16
Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN)
Harshdeep Singh, Yurui Zhu, Giovanni Colavizza, Matteo Romanello
cs.AI · cs.LG
We present EXYGEN (EXplore Your Graphs ENgine), a framework for knowledge graph (KG) understanding that enables conversational access to KGs at scale. We address two questions in sequence. First, how effectively can LLMs perform text-to-SPARQL generation given only automatically derived structured metadata and small graph samples, rather than task-specific fine-tuning? We integrate VoID descriptions and ShEx schemas into a retrieval-augmented...
-
17
Characterizing Job Power Elasticity for Power-Flexible AI Training
Philip Colangelo, Charles Dawson, Shayan Sengupta, Ayse Coskun, Varun Sivaram
cs.AI
Large language model (LLM) training is among the fastest-growing sources of electricity demand in modern data centers, and power availability is a primary bottleneck to continued AI infrastructure growth. Making the power consumption of these workloads flexible could unlock additional power for AI growth, limit increases in electricity prices, and improve the utilization of existing grid infrastructure. However, to realize this flexibility,...
-
18
Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems
Aleksandra Urman, Elsa Lichtenegger, Salima Jaoua, Azza Bouleimen, Robin Forsberg, Corinna Hertweck, Stefania...
cs.AI
Commercial text-to-image systems silently revise user prompts before generating images, a step users typically cannot disable or even see. Yet, existing audits of cultural bias examine only the final images and treat generation as a single pipeline, so they cannot tell where the bias originates. We introduce WORLDVIEW, a multilingual benchmark of 8,960 prompts across 15 languages and 31 language-context pairings. Using it, we audit the...
-
19
Lightweight LiDAR-Based Cone Detection Framework Using Random Forest for Formula Student Driverless
Márk Mező-Kerekes, Péter Praksz, Chang Liu
cs.AI
Reliable, low-latency perception is crucial for Formula Student Driverless vehicles, yet many existing pipelines rely on deep learning and multi-sensor fusion, often requiring GPU acceleration. This paper presents a lightweight LiDAR-only perception pipeline tailored for CPU execution, combining ground removal, IMU-based motion compensation, DBSCAN clustering, and geometric feature-based Random Forest classification. Feature importance...
-
20
Extending SMT Solving with Non-Ground Clause Learning
Yasmine Briefs, Christoph Weidenbach
cs.AI · cs.LO
Quantifier instantiation is currently the main approach to non-ground SMT solving: solvers generate ground instances and solve the resulting ground SMT problems with CDCL(T)-style reasoning. When a conflict is found, conflict analysis learns only a ground clause, even though the conflict comes from instances of non-ground clauses. Yet non-ground reasoning can give exponentially shorter proofs than purely ground reasoning. We propose a...
-
21
ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Maps
Jacopo Dardini, Roberta Calegari
cs.AI
Practical uncertainty quantification (UQ) for large language models must decide, from a single generation, whether a specific answer should be trusted. Existing methods either sample multiple generations, read only output-token probabilities, or reduce the model's internal computation to a single hidden state. We introduce ActMap, a white-box representation that compresses the generation-time hidden- state trajectory (every layer, every...
-
22
From Document Silos to Process Intelligence: A Multi-Layer Knowledge Graph for CMC Process Development
Reza Amirmoshiri, Faryad Sahneh, Yasser Jangjou
cs.AI · cs.MA
Chemistry, Manufacturing and Controls (CMC) process development generates an enormous body of technical information across a multi-stage, knowledge-intensive continuum from drug discovery to commercial manufacturing. This knowledge is traditionally fragmented across functions and heterogeneous formats, causing traceability gaps and significant knowledge-management costs during technology transfer and regulatory filing. We present a modular...
-
23
Published Unlearning Numbers Move Per Checkpoint, and Not Because the Removed Data Survives: An Audit of 263 Released Batch-Normalized Checkpoints
Junlong Shen Xingyu Li
cs.AI · cs.LG
An unlearning audit reads its verdict off numbers that an unlearned model and its retrained reference each publish, and both also ship batch-normalization statistics that no gradient step wrote and no release records. Refitting them on kept data at bit-identical weights moves 47 of 221 released checkpoints past the spread their own release's seeds show, several inside a method whose average does not move: what moves is the checkpoint's...
-
24
The Convention Gap: Towards Measuring Implicit Communication in Cooperative AI Evaluation
Makoto Fukushima, Hua-Dong Xiong, Ehsan Moradi Pari
cs.AI · cs.HC
Cooperative AI agents are evaluated against other AIs, yet human cooperation relies on implicit conventions---shared protocols for reading meaning beyond the literal message---which AI-AI benchmarks may not capture. We propose the \emph{convention gap}, the difference between the failure probability predicted from the literal content of communication and the observed failure rate, as a metric of implicit communication. In the card game...
-
25
Flexible and Interpretable Accent Distance Measurements
Charles McGhee, Mark J. F. Gales, Kate M. Knill
cs.AI
Determining the differences between two speakers' accents is a fundamental task in linguistics and speech technology research. The methodology used to measure these differences depends on the specific research area. A phonetics researcher may demonstrate accent variation by comparing vowel formants in paired recordings of individual words. These results will be interpretable, but the recordings will be time-consuming to collect and may not be...
-
26
RouteRepair: Instance-Level Failure Diagnosis and Targeted Repair in LLM-Based Automated Heuristic Design for Routing Optimization
Binghao Ji, Di Huang, Jiahui Fang, Zhiyuan Liu
cs.AI
Efficient routing optimization is essential to freight transportation, urban logistics, and shared mobility, where high-quality heuristics are often required under limited computational budgets. Recent large language model (LLM)-based automated heuristic design methods can generate effective routing rules, but aggregate evaluation may mask recurrent failures on particular instance structures. To address this limitation, this study develops...
-
27
Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration
Yilin Zhang, Han Jiang, Cai Xu, Ying Liu, Wei Zhao
cs.AI
Heterogeneous model collaboration seeks to exploit the complementary strengths of different models to balance predictive performance and inference cost. Existing approaches typically rely either on trained routers, which tie routing decisions to a fixed task and model pool, or on raw-confidence cascades, whose thresholds lack consistent reliability semantics across heterogeneous models. Consequently, these approaches adapt poorly to changing...
-
28
LLMs as Post-hoc Auditors of Physiological Plausibility in Symbolic Regression: A Clinician-Evaluated Case Study
Jorge López-Varela, J. Ignacio Hidalgo, José-Manuel Muñoz, Omar Costilla-Reyes, Esther Maqueda, Jesus...
cs.AI
Genetic Programming and its variants, such as grammatical evolution, are widely used in Symbolic Regression to derive mathematical expressions from multivariate data. In addition to predictive accuracy, models are appreciated for their potential to provide interpretability, offering explicit equations that relate input variables to outcomes. However, achieving interpretability and plausibility remains challenging, as evolved models may be...
-
29
From Queries to Narratives: Cultural Heritage Data Stories for Knowledge Graph Exploration and Quality Assessment
Tabea Tietz, Torsten Schrade, Etienne Posthumus, Linnaea Söhn, Jonatan Jalle Steller, Jörg Waitelonis, Harald Sack
cs.AI · cs.DL
Cultural-heritage KGs such as the NFDI4Culture-KG contain millions of triples about artworks, music, inscriptions, historical events, and the people and places connected to them. For many users, however, discovering this knowledge can be difficult. While SPARQL can be learned, writing meaningful queries first requires an in-depth understanding of the graph's data model, an investment many domain researchers and practitioners are unwilling to...
-
30
Beyond Confidence: Stability-Aware Test-Time Adaptation for LLM Reasoning
Bincheng Gu, Min Gao, Zongwei Wang, Yibing Bai, Yulan He, Junliang Yu
cs.AI
Test-time adaptation has emerged as a lightweight alternative to costly post-training for improving the reasoning capabilities of Large Language Models (LLMs) on downstream tasks. Predictive entropy provides a model-derived signal for such adaptation, guiding models toward higher-confidence reasoning states without external verifiers or reward models. However, higher confidence does not necessarily imply correctness, as LLMs may remain highly...
-
31
RAMamba-Net: A Reliability-Aware and Mamba-Based Multimodal Fusion Network for Auditory Attention Detection
Xingyi He, Ziwei Wang, Dongrui Wu
cs.AI
Auditory attention decoding (AAD) identifies the attended speaker from physiological signals, supporting neuro-steered hearing devices and natural human-machine interaction. Electroencephalography (EEG) is the dominant modality for AAD but provides incomplete evidence in naturalistic audio-visual scenes, motivating EEG and electrooculography (EOG) fusion. Existing approaches remain limited by weak cross-modal interaction, inefficient temporal...
-
32
Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells
Narcis Marincat
cs.AI
In shared-genome language-model societies, restricted evidence visibility favors reusable, value-indexed latent packet interfaces, whereas the sole high-performing globally visible model in the parent study learned an episode-entangled code. This companion study asks whether independently trained societies share one packet language, where strict zero-shot transfer fails, and whether inherited interface state helps or harms later learning....
-
33
Exploring Diffusion Transformers for Cross-Modal Augmentation in Multimodal Brain State Decoding
Ziwei Wang, Xingyi He, Hongbin Wang, Tianwang Jia, Bohan Fang, Dongrui Wu
cs.AI
Multimodal brain state decoding has largely focused on fusing paired modalities for prediction, but has rarely explored how their correspondence can be further exploited to enrich training data and improve multimodal representation learning. To address this gap, we propose CoMA-DiT, a bidirectional cross-modal Diffusion Transformer for latent augmentation that treats paired modalities as sources of mutual generative supervision rather than...
-
34
AI Exposure and AI Resilience: A Two-Dimensional Assessment Framework for Software and Software-Based Business Model
Paul Darius Mandl, Peter Mandl, Martin Häusl
cs.AI
Artificial intelligence is changing both software production and the economics of software-based business models. Classical technology due diligence mainly examines technical properties such as architecture, scalability, and technical debt. These criteria do not fully capture how AI can affect a company's value proposition, competitive position, margins, or access to customers. This paper develops Artificial Intelligence Exposure and...
-
35
Magenta: Closing the Loop Between Mathematical Reasoning and Lean Verification
Joshua Ong Jun Leang, Haonan Li, Zheng Zhao, Xinyi Shang, Wenda Li, Zhengzhong Liu, Erix Xing, Shay Cohen, Eleonora...
cs.AI
Most of mathematical knowledge has been communicated through so-called informal use of mathematics and natural language. With large language models (LLMs) being highly adept in using natural language, they achieve strong performance, yet not perfect, in informal mathematical reasoning. Restraining LLMs to informal reasoning misses out on the opportunity to use the discrete verification abilities that machines offer through machine-checkable...
-
36
Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents
Minghao Guo, Meng Cao, Sui Zhao, Siyu Ning, Xin Wang, Haoze Zhao, Jiaxuan Yang, Haihong Hao, Mingfei Han, Shunlin...
cs.AI
Deep research agents are increasingly capable of web search, tool use, multimodal evidence analysis, and information synthesis. However, existing benchmarks mainly evaluate medium-horizon exploration and rarely test whether agents can sustain long, dependency-heavy research processes. We introduce Mr.LHDR (Multimodal real-world Long-Horizon Deep Research), a benchmark for evaluating real-world deep research over long, irreducible chains of...
-
37
Routing by Reasoning Need: Trajectory-Aware Decoding Control for Diffusion Vision-Language Models
Yixiang Liu, Zhongxing Xu, Zhonghua Wang, Xiaoying Tang
cs.AI
Diffusion vision-language models generate answers through iterative refinement, exposing intermediate answer trajectories that can be inspected and controlled at inference time. However, this controllability creates a reasoning-need mismatch, where a universal generation length is applied to questions with different reasoning demands. Visually closed questions may be harmed by continued refinement after a stable answer has formed, whereas...
-
38
Memory Compression for High-Fanout Agent Sandboxes
Mengming Li, Ceyu XU, Qijun Zhang, Jiangnan Yu, Xiangfeng Sun, Haohui Mai, Zhiyao Xie
cs.AI · cs.OS
High-fanout agent workloads create a growing memory bottleneck because a single task may spawn many concurrent sandbox sessions. Yet these sandboxes are far from independent: they originate from a shared template and execute related trajectories, exposing substantial template-relative and cross-sandbox memory redundancy. Conventional memory compression is poorly matched to this setting in three fundamental dimensions: how to compress, because...
-
39
Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model
Hyojung Han
cs.AI
We post-train Qwen3.8-27B for Korean response style -- verbosity, list and markdown usage, discourse structure and register -- and measure two behaviours the objective never targets: abstention on ambiguous social questions in KoBBQ, where the benchmark-correct answer is UNKNOWN, and unprompted disclosure in securities guidance. Both move, and the changes are expressed primarily through the model's emission policy: how often it answers and...
-
40
Generating a Consistent Enterprise: Synthesis and Reference-Free Evaluation of Multi-System Business Data
Benjamin Gruenbaum, Doron Porat, Assaf Natanzon, Roy Zavida, Chen Dinachi, Or Itzahary, Omer Niv
cs.AI
Synthetic relational data is normally produced by a model trained on a real dataset, and its quality is measured as the distance to that dataset. This paper describes a generator that has no real dataset at either end. Given an industry, a company size, a business model, a set of business applications, and a random seed, it produces a complete fictional enterprise: a workforce, a customer base, sales deals, support tickets, recorded calls,...
-
41
When Does Text Inform? Benchmarking Information-Theoretic Metrics for Multimodal Time-Series Forecasting
Emma Andrews, Gianmarco Mengaldo
cs.AI · cs.IT
Multimodal forecasting models that combine time series with text annotations promise richer prediction through textual context, but how do we know whether a text annotation meaningfully contributes to the forecasters prediction? This is an information-theoretic question, but to evaluate whether information-theoretic metrics can reliably measure the predictive value an annotation provides, a ground truth benchmark is needed, and none currently...
-
42
Bio-inspired Learning and Decision-Making with Probabilistic In-Memory Computing Hardware: Part 1
Thomas Dalgaty, Eiji Kawasaki, Miguel de Prado, Devendra Vyas, Tommaso Salvatori
cs.AI · cs.LG
Learning and decision-making in animals are often modeled as Bayesian processes, where sensory evidence is integrated with prior beliefs to guide behavior in the face of uncertainty. But what are the inherent neural dynamics that give rise to this ability, and how could they be replicated in computing systems? This abstract discusses a biologically grounded framework in which noisy neural and synaptic dynamics perform inference and learning...
-
43
Predicting Train Delays in Finland Using Machine Learning and Weather Data
Vinicius Pozzobon Borin, Jean Michel de Souza Sant'Ana, Nurul Huda Mahmood
cs.AI · cs.LG
Reliable railway operations depend increasingly on real-time environmental intelligence delivered through wireless sensor infrastructures, a capability that 6G networks will substantially enhance through integrated sensing and edge computing. Adverse weather, particularly in Arctic regions with extreme temperatures and heavy precipitation, remains a leading cause of train delays, yet most prediction approaches rely on raw meteorological...
-
44
AI-Powered Flare Combustion Efficiency Estimation
Afeefa Azam, Iyyakutti Iyappan Ganapathi, Fares Ossama Abdelhafez, Divya Velayudhan, Maregu Assefa Habtie, Hamad...
cs.AI · cs.CV
Achieving high combustion efficiency in flare stacks is crucial for adhering to regulatory standards and controlling the release of hydrocarbons into the environment. Traditional instruments like gas analyzers and hyperspectral cameras are expensive, fragile, and require frequent calibration, which makes them impractical for remote or budget constrained industrial sites. We propose an innovative solution that combines a lightweight...
-
45
Sci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents
Jiaqiang Li, Yajie Yang, Zhiheng Xi, Jiadong Chen, Enyu Zhou, Senjie Jin, Yang Nan, Jiazheng Zhang, Han Wang, Yanxin...
cs.AI
Autonomous research agents are increasingly expected to search the literature, analyze experimental evidence, and generate scientific hypotheses. These capabilities require multi-step evidence grounded reasoning that progressively acquires, integrates, and verifies evidence before reaching a conclusion. Existing multimodal benchmarks, however, largely evaluate final-answer accuracy, leaving open whether predictions are actually supported by...
-
46
NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment
Guoqiang Zhang, Kexin Tan, Ming Zhang, Li Ju, Wenqing Jing, Zhonghan Yue, Jiayi Chen, Shiqiang Wu, Shaofan Liu, Yue...
cs.AI
Large language models (LLMs) are increasingly used in peer review at major AI conferences, yet novelty remains a persistent weak point. Existing benchmarks assess novelty as a single holistic score, making it difficult to diagnose which dimension a model misjudges or whether its evidence is faithful. We present NovGauge, a human-anchored benchmark for fine-grained novelty assessment diagnosis. The benchmark contains 619 paper pairs and 50...
-
47
A Voice-Interactive Multi-Agent System for Smart Operating Rooms: Architecture Design and Key Technologies
Tianxiang Zhou
cs.AI · cs.CL · cs.HC
This paper presents SurgicalRoomAgent, a voice-interactive multi-agent system for smart operating rooms based on large language models (LLMs). The system achieves natural language understanding, device control, intraoperative recording, and surgical report generation through a layered architecture comprising a voice interaction pipeline (wake, ASR, turn detection, agent reasoning, TTS) and an agent core (skill registry, task planner, device...
-
48
CryptoL: Towards Scale Dominance and Physics Constraints Mitigation in Financial Multivariate Time Series Forecasting
Yalda Taheri, Mohammad Hassan Heydari, Armon Rasooli, Maryam Amirshahkarami, Mohammad Ebrahim Mahdavi, Hossein Karshenas
cs.AI · cs.CE · cs.LG
Cryptocurrency forecasting presents a distinctive combination of extreme cross-asset scale heterogeneity, non-stationary dynamics, and structural dependencies among Open, High, Low, and Close (OHLC) variables. We present CryptoL, a unified framework designed to address these challenges within multivariate time-series forecasting. CryptoL evaluates forecasting error in context-normalized coordinates within the RevIN pipeline, preventing...
-
49
An AI-Powered Culturally Aware Chatbot for Stress Detection and Wellness Support among Pakistani University Students Using NLP and Machine Learning
Muhammad Fahad Bashir, Muhammad Afzal
cs.AI
With the existing digital mental health tools specifically developed for Western settings, Pakistani students are exposed to a uniquely compounded stress situation in their university that includes academic, financial, familial, and relational stressors, which have become a serious concern for academic and psychological development of students in Pakistani universities. This paper introduces a new, AI-driven and culturally sensitive stress...
-
50
Agentic Share-of-Search: A Multi-Agent AI System for Competitive Decision-Making in LLM-Mediated E-Commerce
Spandan Ghose Chowdhury
cs.AI · cs.IR
AI shopping assistants increasingly redirect consumer discovery, creating an urgent need for tools that support seller-side competitive decision-making. We present a multi-agent AI system that automates competitive visibility measurement and root cause diagnosis in LLM-mediated ecommerce. The system introduces Agentic Share-of-Search (ASoS) as the decision target, deploys query agents across leading AI platforms, and uses a ReAct-based...
-
51
Can LLMs Follow Medical Expert Logic? A Benchmark for Hierarchical Logical Consistency in Risk-of-Bias Assessment
Jiayu Huang, Zichen Tang, Qianhui Ling, Zemin Kuang, Haihong E
cs.AI
Evidence-based medicine demands strict logical consistency, yet current evaluations of large language models (LLMs) prioritize superficial label matching over genuine reasoning. We introduce LogiMed-RoB, a benchmark grounded in Cochrane Risk of Bias (RoB) 2.0 expert logic, comprising 860 randomized controlled trials (RCTs) and 14,820 queries. It evaluates models under the Hierarchical Logical Consistency (HLC) framework across four...
-
52
SemVerBench: Benchmarking LLM Comprehension of Version-Constraint Resolution Semantics
Qibai Chen, Zeming Liu
cs.AI · cs.SE
Large language model (LLM) coding agents constantly decide whether a version satisfies a constraint such as ^1.2.3 or >=2.0,<3, yet their grasp of version-constraint semantics has never been measured directly. We introduce SemVerBench, the first benchmark of LLM version-constraint resolution semantics across three ecosystems (npm, PEP 440, Cargo): 240 machine-checkable items with unique answers, built author-neutrally from four balanced...
-
53
Debate-to-Skill: Capability-Bound Process Supervision for Industrial Query-to-Agent Annotation
Shiyu Zhang, Leisheng Cheng, Huifu Li
cs.AI
Industrial query-to-agent matching fails when topical relevance is mistaken for executable capability, especially on long-tail and boundary-sensitive requests. We formulate annotation as \emph{capability-bound process supervision} and instantiate it with Debate-to-Skill, which uses reusable decision principles, structured deliberation, verifier-based verdict extraction, and disagreement-driven refinement. On an industrial Query2Agent...
-
54
Breaking Predictions Is Not Enough: Specified-Foil Counterfactuals for Temporal Graphs
Minwoo Yu, Young-guk Ha
cs.AI
Temporal graph counterfactual explanations typically change past events to change or invalidate an original prediction, while leaving its replacement unspecified. Yet a user facing a predicted outcome often asks which past conditions would make a particular alternative occur instead. We formulate this destination-specific question as the Specified-Foil Counterfactual: given an original prediction A and a foil B fixed before search, find a...
-
55
DRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat
Junlin Liu, Chengwei Li, Yang Gao, Hui Chang, Xinchen Zhang, Zhijun Zhao, Hao Zhao
cs.AI
Multi-Agent Reinforcement Learning (MARL) has emerged as a pivotal paradigm for complex decision-making in autonomous systems and air combat. While MARL has demonstrated significant potential in air combat, achieving sophisticated tactical coordination remains a non-trivial challenge. This difficulty is largely attributed to two primary limitations: (1) the absence of structured relational modeling hinders agents from capturing complex,...
-
56
Autonomous Chemical Mechanistic Discovery through Agentic Reasoning and Validation
Dong Li, Sixuan Mi, Zihao Ye, Huan Xiong, Tao XU, Tong Zhu, Aijia Zhang, Junqi Gao, Kaiyan Zhang, Shijie Wang, Bowen...
cs.AI
Unraveling reaction mechanisms is central to modern chemistry, yet automating these investigations remains challenging because computational workflows still rely heavily on expert intervention. Here we introduce ARCHE, an autonomous agentic system that integrates a general-purpose reasoning model, a domain-specialized computational chemistry model, and a structured tool registry to transform mechanistic inquiry into a scalable,...
-
57
The Oligarch Barely Steers Model Collapse in Multi-Model Ecosystems
Yangze Liu, Zhongyi Han
cs.AI · cs.CL · cs.LG
AI-generated text is flowing back into the training corpora of the next generation of models. Recursive training on it drives model collapse, and recent work extends the setting to many models feeding one another -- but almost always with the market split evenly, while real generative AI is an oligopoly. Concentration raises two worries: fewer, more uniform sources may make collapse faster, and later models may be dragged toward the...
-
58
Same Day, Same Story; One Day Ahead, a Different Signal: The Dual Validity of Financial Sentiment
AS Aravinthkakshan, Laven Srivastava, Harsh Nandwani
cs.AI · cs.CL · cs.SI
Financial NLP has a standard workflow: validate a sentiment tool against human labels, then trust it to extract market signal. This assumes the two evaluations measure the same thing. We test that assumption in a setting where both can be measured at once: a corpus of securities class actions (2002-2025) linking 70,500 X messages to abnormal stock returns, with a single-annotator human labelled gold sample. Running five instruments (VADER,...
-
59
KuaiRP Series Role-playing Models Technical Report
Yipeng Wang, Ziwei Zhang, Jiahui Zhang, Qi Gan, Kai Sheng
cs.AI · cs.CL
This paper introduces the complete technical solution for the KuaiRP series of role-playing models. We aim to achieve four core objectives for a dedicated role-playing model: simplified prompt engineering, highly stable output quality, built-in domain world knowledge, and high-efficiency deployment with a small parameter size. However, effectively injecting deep domain knowledge often leads to a severe catastrophic forgetting of the model's...
-
60
Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation
Koutian Wu, Junjie Zhou, Ergan Shang, Jiayu Wang, Pengqian Han, Junkai Wang, Wanghan Xu
cs.AI · cs.IR
Benchmark researchers and developers of large language models (LLMs) and other AI systems need to find relevant evaluations, locate their benchmark datasets and code, and understand the settings behind reported scores. We present Benchmark Radar, a living database and search engine for retrieval and discovery of AI benchmarks, covering LLM evaluation, agentic and tool-use benchmarks, coding, reasoning, safety, and domain-specific evaluations....
-
61
MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG
EunKyeong Lee, Kyeong-Jin Oh, Jinwon Kim, Hye Woo Lee, Minsang Song, Hyeongjun Jang, Junyoung Youn
cs.AI
Graph Retrieval-Augmented Generation (GraphRAG) can connect evidence distributed across a corpus graph, but most systems use largely shared exploration procedures across queries. This creates a structural mismatch: direct facts may need compact local neighborhoods, comparisons need balanced coverage of multiple targets, and mediated questions may require deeper paths through weakly related connectors. We present Mosaic, a training-free...
-
62
Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning
Bin Lei, Yu Li, Prafulla Kumar Choubey, Jiaxin Zhang, Becky Xiangyu Peng, Qinyuan Ye, Kartik Narayan, Caiwen Ding,...
cs.AI
Tree-structured rollouts give critic-free reinforcement learning with verifiable rewards (RLVR) step-level credit: fork a chain at an intermediate point, and sibling outcome differences estimate step value. Each fork adds sampling cost, so realistic budgets typically allow only a few forks per chain. A fork placed where the outcome is already largely settled yields siblings that mostly agree and provide almost no credit signal; hence, for a...
-
63
Grounding Agent Memory: Environment-Probing Curation for Enterprise Agents
Susheel Suresh, Hazel Mak, Sahil Bhatnagar, Chhaya Methani, Alejandro Gutierrez Munoz
cs.AI · cs.SE
Persistent memory is entering production-oriented agent platforms to help long-horizon agents accumulate experience across sessions. Yet a post-task curator agent restricted to completed trajectories can preserve errors, overgeneralize partial evidence, or retain stale knowledge. We introduce environment-probing curation, a deployment-compatible extension that gives an existing asynchronous curator agent least-privilege, read-only world tools...
-
64
The Agent Incident Registry: Toward Preventing Repeated AI Agent Failures
Divyanshu Kumar, Rohith HN, Nitin Aravind Birur, Sahil Agarwal, Prashanth Harshangi
cs.AI
AI agents increasingly act through tools and delegated authority, but general incident repositories rarely capture the mechanisms needed to compare public failures with agent-security evaluations. We present the Agent Incident Registry (AIR), a source-linked catalog containing \N{} records of agent-related events disclosed from \Yfirst{} through \Ylast{}. Each record includes supporting evidence, a stable identifier, and missingness-aware...
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.