cs.AI · 2026-06-02 · No. 13
Artificial Intelligence, 2026-06-02.
48 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
48 entries-
01
ClinEnv: An Interactive Multi-Stage Long Horizon EHR Environment for Agents
Yuxing Lu, Yushuhong Lin, Wenqi Shi, J. Ben Tamo, Xukai Zhao, Jinzhuo Wang, May Dongmei Wang
cs.AI · cs.CL · cs.ET · cs.MA
Clinical practice is not the selection of an answer from enumerated options: a physician gathers heterogeneous information incrementally and commits to sequential, irreversible decisions under uncertainty. Static benchmarks cannot probe and existing interactive medical benchmarks each compromise on at least one of them. We present ClinEnv, an interactive benchmark that evaluates LLMs as attending physicians over real inpatient admissions...
-
02
Tracking the Behavioral Trajectories of Adapting Agents
Jonah Leshin, Manish Shah, Ian Timmis
cs.AI
Text files such as skill files, memory files, and behavioral configuration files play a central role in defining how modern agents act. Through edits by humans or the agents themselves, these files may evolve over time, directly steering the agent's behavior in future interactions. We present a methodology and framework for measuring agent $traits$ by defining traits as directions in the embedding space of a text embedding model. We train a...
-
03
SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
Hao Li, Jingkun An, Zijun Song, Pengyu Zhu, Rui Li, Hao Wang, Wendi Feng, Yesheng Liu, Lijun Li, Jin-Ge Yao, Lei Sha
cs.AI · cs.CL
Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax. Existing methods mitigate this by balancing dual objectives, which heavily rely on massive general-purpose data or auxiliary reward models. In this paper, we argue that, because safety features are inherently sparse within the output distribution, alignment requires localized modifications rather than global trade-offs....
-
04
Bridging the Last Mile of Time Series Forecasting with LLM Agents
Yuhua Liao, Zetian Wang, Qiangqiang Nie, Zhenhua Zhang
cs.AI
Time series forecasting has advanced rapidly, especially with the emergence of foundation models that show strong zero-shot performance on numerical extrapolation. However, in real-world forecasting settings, a statistically plausible baseline is rarely the final forecast used in practice. Before a forecast becomes decision-ready, it often needs to be revised using weakly structured business context such as holiday effects, campaign plans,...
-
05
RASER: Recoverability-Aware Selective Escalation Router for Multi-Hop Question Answering
Yuyang Li, Zihe Yan, Tobias Käfer
cs.AI
Multi-hop question-answering systems often use expensive retrieval on every question. They may decompose the question, run several retrieval rounds, or search through bridge entities before answering. All of these strategies rely on repeated LLM calls to rewrite or decompose the question, which increases extra token cost, and it is not fitting when the LLM budget is tight. However, our analysis shows that lots of multi-hop questions are...
-
06
Iteris: Agentic Research Loops for Computational Mathematics
Leheng Chen, Zihao Liu, Wanyi He, Bin Dong
cs.AI · cs.LG
Recent advances in large language models and agentic AI systems have enabled significant progress in mathematical discovery, from solving competition problems to tackling research-level conjectures. However, open problems in computational mathematics have received comparatively less attention: research in this area often requires not only proofs but also numerical experimentation, adversarial constructions, and algorithm design. In this...
-
07
MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation
Wenhao Wang, Peizhi Niu, Gongyi Zou, Xiyuan Yang, Jingxing Wang, Haoting Shi, Yaxin Du, Jingyi Chai, Xianghe Pang,...
cs.AI
The Model Context Protocol (MCP) has emerged as a transformative standard for connecting large language models (LLMs) with external data sources and tools, and has been rapidly adopted across personal applications and development platforms. However, existing benchmarks predominantly focus on generic information-seeking tools and fail to capture the practical challenges posed by personal social applications, where tools interact with...
-
08
AGENTCL: Toward Rigorous Evaluation of Continual Learning in Language Agents
Yiheng Shu, Bernal Jiménez Gutiérrez, Saisri Padmaja Jonnalagedda, Yuguang Yao, Huan Sun, Yu Su
cs.AI · cs.CL
Language agents spend substantial inference time solving individual tasks, yet the experience acquired in one episode is often underutilized in future episodes. Continual learning expects an agent to accumulate reusable experience across a stream of tasks, improve over time, and avoid interference from irrelevant experiences. Unfortunately, existing benchmarks struggle to evaluate continual learning in language agents rigorously. Most efforts...
-
09
Beyond One-shot: AI Agents for Learning in Field Experiments
Junjie Luo, Ritu Agarwal, Gordon Gao
cs.AI
Organizations routinely run experiments for A/B testing, yet the data generated from one experiment is underutilized to inform subsequent intervention design. Significant barriers exist to extracting actionable knowledge from prior experimental data to inform new interventions. We study whether tool-augmented agentic AI can automatically learn from experimental data to generate new interventions in subsequent experiments. Through two-stage...
-
10
HLL: Can Agents Cross Humanity's Last Line of Verification?
Xinhao Song, Su Su, Sirui Song, Hongliang Wu, Wen Shen, Zhihua Wei, Gongshen Liu, Linfeng Zhang, Dongrui Liu
cs.AI · cs.CL · cs.CV · cs.LG · cs.MM
Multimodal agents are increasingly expected to operate interfaces on behalf of users, raising a central deployment question: can they truly substitute for humans in workflows that services deliberately protect against automation? CAPTCHA verification makes this question concrete. It is not merely a visual puzzle, but a human-verification boundary placed before account creation, content access, form submission, and other protected actions. We...
-
11
Food Noise & False Safety: A Systematic Evaluation of How LLMs Fail to Adapt to Eating Disorder Queries with Clinician Feedback
Giulia Pucci, Emily Hemendinger, Ruizhe Li, Gavin Abercrombie, Tanvi Dinkar, Arabella Sinclair
cs.AI · cs.CL
Recent evidence shows that people with eating disorders (EDs) are increasingly seeking guidance, advice, and emotional support from Large Language Model (LLM)-based chat systems. Although these systems are not designed to provide clinical advice, their perceived expertise, neutrality and accessibility make them a frequent, albeit risky, source of support. This paper investigates potential patterns of interaction between users with EDs and...
-
12
LLM-Evolved Pattern Generators for Optimal Classical Planning
Windy Phung, Dominik Drexler, Arnaud Lequen, Jendrik Seipp
cs.AI
Learned heuristics have recently become a competitive alternative to traditional domain-independent heuristics for satisficing planning. Existing approaches, however, focus on improving search guidance rather than guaranteeing admissibility, which makes them unsuitable for optimal classical planning. We present the first method for learning domain-dependent heuristics that are admissible by design and thus preserve the optimality guarantees...
-
13
Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization
Yusuke Ohtsubo, Kota Dohi, Koichiro Yawata, Koki Takeshita, Tatsuya Sasaki
cs.AI
Precise parametric control over circuit geometry is essential for semiconductor inspection, yet obtaining sufficient real training data remains costly. Although generative models such as diffusion models and Generative Adversarial Networks (GANs) can augment training data, they cannot guarantee the nanometer-scale geometric accuracy required for metrology tasks. We propose a visual program synthesis framework in which a Vision-Language Model...
-
14
AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence Design
Sahil Rahman, Maxx Richard Rahman
cs.AI · q-bio.QM
Protein language models (PLMs) are passive oracles: they generate sequences in a single forward pass with no mechanism to consult external biophysical feedback or redirect generation when a candidate violates thermodynamic or structural constraints. We introduce AgentPLM, which addresses this by equipping a pre-trained PLM with i) Reasoning-Augmented Decoding (RAD), which interleaves autoregressive generation with tool calls (ESMFold, FoldX,...
-
15
A Mathematical Conflict Framework for Contextual Data Modulation
Hakan Emre Kartal
cs.AI · cs.LG · math.DS
In this study, a generalized operator-based mathematical conflict framework is presented to explicitly represent structural discrepancies between raw data and contextual data. The proposed structure treats conflict as a local, directional, and context-sensitive quantity, integrating components such as weighting, scale behavior, and output mapping under a unified abstract operator. Without being reduced to a specific learning algorithm or...
-
16
Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models
Steffen Knoblauch, Hao Li, Gengchen Mai, Konstantin Klemmer, Song Gao, WenWen Li
cs.AI
Earth Observation (EO) has fundamentally transformed the monitoring of environmental processes and human activities up to planetary scale. Recent advances in self-supervised learning have given rise to Earth Observation Foundation Models (EOFMs), which leverage petabyte-scale unlabeled EO data to learn transferable representations across a wide range of downstream geospatial tasks. Despite these advances, current EOFMs remain largely confined...
-
17
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
Pengcheng Jiang, Zhiyi Shi, Kelly Hong, Xueqiang Xu, Jiashuo Sun, Jimeng Sun, Hammad Bashir, Jiawei Han
cs.AI · cs.CL · cs.IR
Search agents are often trained as policies over growing transcripts: the model must decide how to search while also remembering what it has seen, which evidence is useful, which constraints remain open, and which claims have actually been checked. We argue that this formulation puts too much routine state management inside the policy: reinforcement learning is forced to optimize both semantic search decisions and recoverable bookkeeping that...
-
18
COMAP: Co-Evolving World Models and Agent Policies for LLM Agents
Youwei Liu, Jian Wang, Hanlin Wang, Wenjie Li
cs.AI · cs.CL
Equipping language agents with world models enables them to anticipate environment dynamics and evaluate candidate actions before execution. However, existing textual world models are typically fixed after training, preventing them from adapting to the on-policy state-action distributions induced by an evolving agent. Meanwhile, agent-improvement methods often rely on external rewards or verifiers, limiting their applicability in realistic...
-
19
MOC: Multi-Order Communication in LLM-based Multi-Agent Systems
Yao Guan, Lin Wang, Zhihu Lu, Ziyi Wang, Wenzhu Yan, Qiang Duan
cs.AI
Despite the remarkable progress of Large Language Model (LLM) based Multi-Agent Systems, most research focuses on optimizing coordination topology while largely underexploring the equally critical problem: how to transmit and optimize messages among agents effectively? Current communication schemes typically rely on the direct concatenation of first-order neighbor responses, which induces a restricted evidence receptive field and leads to the...
-
20
SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training
Zhongyu He, Yuanfan Li, Fei Huang, Tianyu Chen, Siyuan Chen, Xingyang Li, Meng Hsuan Yu, Xiangrong Liu, Leyi Wei, Lu...
cs.AI · cs.LG
Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or persistent skill retrieval at inference, increasing engineering complexity, context length, and deployment latency. We propose Self-Internalizing Reinforcement learning with Intrinsic skills (SIRI), a three-phase framework that enables agents to discover, validate, and internalize skills without...
-
21
Coordination Graphs for Constrained Multi-Agent Reinforcement Learning
Santiago Amaya-Corredor, Miguel Calvo-Fullana, Anders Jonsson
cs.AI
Constrained Multi-agent reinforcement learning (CMARL) faces two intertwined challenges: the joint action space grows exponentially with the number of agents, and additional requirements couple agents in ways that reward structure alone does not capture. We introduce Coordination Graphs for Constrained Multi-Agent Reinforcement Learning (CG-CMARL), a framework that addresses both challenges by combining coordination graphs with Lagrangian...
-
22
Forget Attention: Importance-Aware Attention Is All You Need
Soohyeong Shin, Yeongwook Yang
cs.AI · cs.CL · cs.LG
Combining attention's global retrieval with the sequential importance signal of state space models (SSMs) is the open challenge of hybrid language modeling. Transformers see everywhere but cannot prioritize; SSMs know what matters but cannot revisit. Existing hybrids -- Jamba (block level) and Hymba (head level) -- place the two in separate compartments, so neither informs the other during the attention computation itself. We propose SISA...
-
23
Repair Before Veto: Repair-Augmented Constraint Learning for Contextual Decisions
Yifan Wang
cs.AI
Hard constraints are usually treated as terminal vetoes: once a candidate violates a requirement, the learned rule rejects it and any repair is handled outside the decision semantics. This misses a common deployed regime in which the system already knows a finite menu of modifications, such as adding a ticket option, changing a configuration, or requesting an available service upgrade. Existing constraint-learning, soft-relaxation, and...
-
24
POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems
Iñaki Dellibarda Varela, R. Sendra-Arranz, Pablo Romero-Sorozabal, J. M. Valverde-García, Annemarie F. Laudanski,...
cs.AI
Orchestrating Large Language Models into Multi-Agent Systems (LLM-MAS) has unlocked remarkable reasoning capabilities, yet emergent failures and hallucinations that resist characterisation block their deployment in safety-critical domains -- a gap made legally untenable by emerging AI regulation. Existing evaluation paradigms share a common flaw: centralised judgment creates single points of failure and demands domain-specific expertise. Here...
-
25
CEON: Circular Economy Ontology Network
Huanyu Li, Els de Vleeschauwer, Robin Keskisärkkä, Mikael Lindecrantz, Mina Abd Nikooie Pour, Ying Li, Ben De...
cs.AI
Increasing the circularity of resource use in our society has been recognized as a path to sustainability, i.e., transitioning into a more circular economy. There are many different circular strategies to do so, such as reusing products and components, refurbishing and remanufacturing used products, or recycling left-over or used materials. To enable these strategies, it is necessary to share information at the infrastructure level and to...
-
26
From Capability Models to Automated Planning: An AAS-Native Approach for Automatic PDDL Generation
Hamied Nabizada, Thomas Wirt, Luis Miguel Vieira da Silva, Felix Gehlhoff, Alexander Fay
cs.AI
Engineers designing production systems need to verify that a given layout supports all required production sequences. Automated planning techniques can answer such questions, but formulating the required planning problems in the Planning Domain Definition Language (PDDL) demands specialized expertise that production engineers typically lack. Asset Administration Shells (AAS) have emerged as the standardized Digital Twin for industrial assets...
-
27
An Abstract Worlds Semantic Framework for Belief Change Operators
Daniel Grimaldi, M. Vanina Martinez, Ricardo O. Rodriguez
cs.AI
This article proposes a set-theoretic framework for belief change, called Abstract Worlds Semantics, in which no logical syntax is assumed. Inspired by Grove's (1988) results, our approach treats worlds as primitive elements, over which world contraction and world revision operators are defined. This semantic framework enables a unified analysis of belief change models. Within this framework, we unify classical and non-prioritized belief...
-
28
S3TS: Stochastic Scenario-Structured Tree Search for Advanced Planning Under Uncertainty
Fabio Pavirani, Bert Claessens, Pierre Pinson, Chris Develder
cs.AI · eess.SY
Effective scheduling in the energy sector is essential to ensure the reliable operation of electrical grids and their connected assets by, for instance, optimizing the dispatch of generation units and storage systems. An effective planning strategy must (a) accommodate advanced and potentially non-linear system models -- exploiting the increasing data availability of modern grids, and (b) explicitly handle uncertainties arising, for instance,...
-
29
Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning
Liuji Chen, Dianxing Tang, Xing Shi, Dingshuo Chen, Qiang Liu, Shu Wu, Liang Wang
cs.AI
Agentic reinforcement learning can induce tool abuse, where models overuse external tools even for queries solvable by internal reasoning. Existing approaches mitigate this issue with uniform tool-use penalties or hard limits, which reduce tool frequency but may also suppress useful tool-assisted exploration. We propose EAPO, an Efficient Agentic Policy Optimization framework that learns selective tool use. EAPO introduces tool-free...
-
30
BADGER: Bridging Agentic and Deterministic Evaluation for Generative Enterprise Reasoning
Shannon Serrao, Soumitra Chatterjee, Dorina Strori, Abhishek Sharma, Nathan Miller
cs.AI
Enterprise AI systems that translate natural language into SQL queries and orchestrate multi-step agentic reasoning pipelines require evaluation approaches fundamentally different from academic benchmarks. Spider and BIRD established execution-accuracy protocols; G-Eval and RAGAS advanced LLM-based assessment; and recent work such as Spider 2.0, BEAVER, and BIRD-Interact has begun to address enterprise and agentic dimensions. No single...
-
31
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
Jiaming Wang, Ziteng Feng, Jiangtao Wu, Ruihao Li, Qianqian Xie, Yuxiang Ren, He Zhu, Xueming Han, Fanyu Meng,...
cs.AI
Deep-research agents solve tasks through long trajectories of search, tool use, evidence inspection, and answer synthesis. Evaluation based on final answers shows whether an agent succeeds, but not which parts of the trajectory make the answer unreliable. We study span-level error localization for deep-research agents. We collect 2,790 real trajectories from two agent frameworks, three backbone models, and three benchmarks, convert raw logs...
-
32
eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion
Xiang Li, Jiwei Wei, Ke Liu, Yitong Qin, Jinyu Guo, Malu Zhang, Peng Wang, Yang Yang
cs.AI
While Large Language Models (LLMs) achieve impressive performance on multi-step reasoning tasks, their reliability is persistently hindered by critical limitations such as unconstrained hallucinations and poor numerical computation. Fundamentally, these issues arise because standard models treat reasoning as a transient, one-off generation process rather than retaining and refining successful procedural logic. To address these challenges, we...
-
33
Explainable Data-driven Deep Reinforcement Learning Methods for Optimal Energy Management in Buildings
Hallah Shahid Butt, Qiong Huang, Gökhan Demirel, Kevin Förderer, Erfan Tajalli-Ardekani, Simnon Waczowicz, Luigi...
cs.AI
The increasing integration of renewable energy sources into power systems, particularly in buildings equipped with photovoltaic (PV) panels and energy storage systems, introduces significant complexity in energy systems. Volatile power generation, varying electricity tariffs, and increased entities, e.g., PV systems, and heat pumps, have increased the complexity and made the system harder to operate. This leads to the demand for additional...
-
34
Topological texture analysis of microscopy images of dynamic casein gelation and its relation to rheological properties
Zahra Tabatabaei, Diana Soto Aguilar, Jose C. Bonilla, Mathias P. Clausen, Jon Sporring
cs.AI · cs.CV · physics.bio-ph
We propose a novel computational toolbox that integrates Topological Data Analysis (TDA), Differential Box Counting (DBC), Multifractal Partition (MFP), and Local Binary Patterns (LBP), applied to time-lapse super-resolution STED microscopy images of sodium caseinate gelation induced by glucono-delta-lactone (GDL) at 30 °C and 40 °C and two GDL concentrations (1.8% and 3.5% w/v). TDA tracked topological loops, closed ring-like structures...
-
35
RL-ACRGNet: Reinforcement Learning-Based Chest Radiology Report Generation Network
Yogesh Kumar Meena, Saurabh Agarwal, K. V. Arya
cs.AI · cs.LG
Medical imaging interpretation is a foundational pillar of modern clinical diagnostics, yet the manual generation of radiology reports remains a time-consuming process prone to interpretation inconsistencies. Within the field of medical AI, automating these descriptions through deep learning promises to streamline clinical workflows and standardise diagnostic output. However, accurate disease detection and precise report generation remain...
-
36
Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery
Ekaterina Alimaskina, Darya Rudas, Denis Shveykin, Gleb Molodtsov, Pavel Vasiliev, Aleksandr Beznosikov
cs.AI · cs.LG
Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive. While low-bit quantization reduces per-token decoding cost, we show that aggressive 2-bit inference can fail to deliver end-to-end speedup because instability in the generation process inflates total token count. Instead of merely lowering answer accuracy, 2-bit quantization often produces much longer traces with repetitive loops, budget exhaustion,...
-
37
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
Lichao Wang, Zhaoxing Ren, Tianzhuo Yang, Jiaming Ji, Chi Harold Liu, Yaodong Yang, Juntao Dai
cs.AI · cs.CL · cs.CY
As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their action spaces offers agents unsafe capabilities and underscores the risk of power-seeking. While broad action space and greater environment influence are essential for task fulfillment, they create a fragile risk surface where minor errors or hallucinations are magnified into catastrophic...
-
38
An NLP-Driven Framework for Curriculum-Labor Market Alignment: Schema-Constrained LLM Extraction, ESCO-Anchored Semantic Matching, and Multi-Dimensional Gap Quantification
Sherzod Turaev, Mary John, Mamoun Awad, Nazar Zaki, Khaled Shuaib
cs.AI
Schema-constrained information extraction from diverse educational and labor-market corpora remains an open challenge in natural language processing because existing pipelines rely primarily on lexical-surface methods that cannot recover implicit competencies, lack grounding in shared taxonomies, and provide no formal measures of extraction reliability or document-level completeness. To address these limitations, this paper proposes a...
-
39
Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks
Fabian Hoppe, Melven Röhrig-Zöllner, Philipp Knechtges
cs.AI · cs.SE
We consider LLM-based algorithm development through a case study on contractionorder optimisation for tensor networks with OpenEvolve. We pay particular attention to the choice of the LLM as well as design choices such as evaluation metric and test instances. Our results highlight both the promise of verifier-guided evolutionary coding agents for algorithm development/improvement and the continuing importance of evaluation, validation, and...
-
40
AutoMedBench: Towards Medical AutoResearch with Agentic AI Models
Junqi Liu, Salena Song, Yuhan Wang, Jiawei Mao, Hardy Chen, Xiaoke Huang, Tianhao Qi, Pengfei Guo, Yucheng Tang,...
cs.AI
Autonomous agents are increasingly expected to support end-to-end medical-AI research workflows, moving beyond isolated prediction tasks or short-form clinical question answering. However, existing medical agent benchmarks primarily evaluate final outputs, providing limited visibility into agent behavior within the research process. To address this gap, we present AutoMedBench, a workflow-aware benchmark for autonomous medical-AI research...
-
41
VET: A Framework for Analyzing AI Discourse
Meredith Ringel Morris
cs.AI
Public discourse on AI has become polarized; exaggerated positions on AI in traditional and social media threaten the development of AI Literacy among the general public. In this article, I introduce the VET Framework, a method for categorizing AI discourse along the dimensions of valence, effectiveness, and trajectory. I show how this framework can be used to identify, compare, and critique prevalent narratives of AI Hype, AI Doom, AI...
-
42
SMH-Bench: Benchmarking LLM Agents for Environment-Grounded Reasoning and Action in Smart Homes
Kuan Li, Shuo Zhang, Huacan Wang, Fangzhou Yu, Zecheng Sheng, Yi Gu, Weipeng Ming, Lei Xue, Chen Liu, Sen Hu,...
cs.AI
Smart homes are evolving toward complex state-dependent living environments, requiring Large Language Models (LLMs) to reason over user intent, preferences, and multi-device interactions. However, existing smart-home benchmarks often focus on static instruction-to-API mapping or limited simulations, failing to evaluate whether LLMs can reason, interact, and act reliably in realistic household scenarios. To address these limitations, we...
-
43
Bayesian Spectral Emotion Transition Discovery from Multi-Annotator Disagreement
Keito Inoshita, Takato Ueno
cs.AI
Emotions evolve through the dynamics of conversation, and understanding their transition structure is foundational to applications ranging from mental-health screening to dialogue systems. However, existing studies typically compress multi-rater judgments into a single hard label by majority voting, discarding the uncertainty signal needed to understand turn-to-turn transitions. In this article, we propose Bayesian Spectral Emotion Transition...
-
44
Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation
Tianjiao Li, Kai Zhao, Xiang Li, Yang Liu, Huyang Sun
cs.AI
Traditional Video Quality Assessment (VQA) focuses narrowly on aesthetic fidelity, overlooking the complex social dynamics that define quality in User-Generated Content (UGC). In this work, we propose a paradigm shift from signal-centric metrics to human-centric resonance assessment. We introduce CASTER (Community-Aware Assessment of Social Textual Engagement and Resonance), a new task that evaluates whether a UGC item achieves positive...
-
45
Physically-Constrained Mamba-SDE for Remaining Useful Life Prediction under Irregular Observations
Deyu Zhuang, Peiliang Gong, Yang Shao, Liyuan Shu, Qi Zhu, Xiaoli Li, Daoqiang Zhang
cs.AI
Accurate Remaining Useful Life prediction is critical for industrial predictive maintenance. However, real-world deployment is challenging due to the irregular nature of sensor observations, characterized by asynchronous sampling, burst missingness, and temporal jitter. Compounding this issue, purely data-driven models often generate physically implausible degradation trajectories that violate the irreversible nature of damage accumulation....
-
46
Absorbing Complexity: An Interaction-Native Knowledge Harness for Financial LLM Agents
Ailiya Borjigin, Igor Stadnyk, Ben Bilski, Maksym Chikita, Dmytro Kyrylenko, Sofiia Pidturkina, Julia Stadnyk
cs.AI · cs.CE
Financial AI agents often fail for a simple reason: they make users carry the complexity. A user must repeatedly restate goals, risk preferences, portfolio context, past judgments, and shifting market assumptions, while the agent answers, retrieves, acts, and forgets. In finance, this is not just inconvenient. In tasks such as market analysis, copy-trading review, and trade preparation, forgotten context and stale memory can create latency,...
-
47
EVA-Net: Subject-Independent EEG Motor Decoding with Video-Derived Motor Priors
Ziyuan Li, Yueyu Sun, Yimeng Zhang
cs.AI
Practical non-invasive Brain-Computer Interface (BCI) systems require EEG decoders with strong cross-subject generalization and minimal calibration. However, inter-subject variability and signal non-stationarity often entangle motor semantics with subject-specific noise, limiting subject-independent decoding. Recent multimodal approaches use text as a semantic anchor, yet text provides sparse and static supervision for inherently dynamic...
-
48
WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis
Shuo Lu, Yinuo Xu, Kecheng Yu, Siru Jiang, Yongcan Yu, Yubin Wang, Haitao Yang, Yuxiang Zhang, Bin Wang, Ran He, Jian Liang
cs.AI
Large language models (LLMs) are increasingly asked not only to write static interfaces, but to construct executable interactive worlds from natural language. Browser-native 3D, commonly built with Three.js, is a natural next frontier: generated programs must integrate assets, obey spatial and physical constraints, and keep user-facing controls synchronized with hidden runtime state. Existing web-generation benchmarks and evaluators, however,...
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.