cs.AI · 2026-07-18 · No. 57
Artificial Intelligence, 2026-07-18.
59 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
59 entries-
01
Pretraining Data Can Be Poisoned through Computational Propaganda
Victoria Graf, Hannaneh Hajishirzi, Noah A. Smith, David Kohlbrenner, Kyle Lo
cs.AI · cs.CL
Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate. Prior work on poisoning pretraining data has largely exploited established data sources such as Wikipedia, which do not represent the large scale and heterogeneity typical of pretraining corpora, and has ignored the interaction between poisoned data and data curation pipelines. We demonstrate that poisoning attacks on pretraining data...
-
02
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
Yuyao Zhang, Junjie Gao, Zhengxian Wu, Jiaming Fan, Jin Zhang, Shihan Ma, Yao Yao, Weiran Qi, Chuyan Jin, Guiyu Ma,...
cs.AI · cs.IR
Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents. However, as interaction histories grow, agents increasingly struggle to track task progress. When search attempts fail to yield useful evidence, current single- and multi-agent systems can become trapped in repetitive loops, wasting search budgets and ultimately compromising the quality and completeness of the final...
-
03
teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data
Qiwei Li, Jorge Ortiz
cs.AI · cs.HC
Traffic agencies now have access to large volumes of video-derived data for studying safety and congestion. Most of these data are observational and collected without interventions, which makes causal questions such as "How would rain change traffic density?" difficult to answer. We present teLLMe, a system for exploratory causal analysis of urban driving datasets. The system starts from a structured event table built from dashcam annotations...
-
04
AutoSynthesis: An agentic system for automated meta-analysis
Moein Taherinezhad, Sebastian Maier, Gerardo Vitagliano, Francesco Pierri, Stefan Feuerriegel
cs.AI
Evidence synthesis is crucial for turning primary research into reliable knowledge for science, medicine, education, and policy. Yet, quantitative evidence synthesis remains largely manual and difficult to scale. Here, we introduce AutoSynthesis, an end-to-end multi-agent system for automated meta-analysis. Given a research question in natural language, AutoSynthesis formulates a search strategy, retrieves scientific literature, screens...
-
05
When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space
Weimeng Wang, Ziqiang Wang, Zihang Zhan, Chuanpu Fu, Qi Li, Ke Xu
cs.AI · cs.CR
Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become unsafe once grounded in the physical world. We study whether this physically grounded danger is the same safety problem as ordinary text-level content danger. Through hidden-state direction analysis and random-split null tests, we show that content danger (CD) and physical danger (PD) form separable...
-
06
Self-Evolving Human-Centered Framework for Explainable Depression Symptom Annotation
Hoang-Loc Cao, Van Pham, Truong Thanh Hung Nguyen, Phuc Truong Loc Nguyen, Phuc Ho, Veronica Whitford, Hung Cao
cs.AI · cs.HC · cs.MA · cs.MM
Annotation quality is a major bottleneck in building reliable and explainable artificial intelligence (XAI) systems for mental health research. In depression-related datasets, labels are often assigned without structured evidence, symptom-level justification, or traceable alignment with the criteria of the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, Text Revision (DSM-5-TR), limiting both transparency and downstream...
-
07
Plover: Steering GUI Agents through Plan-Centric Interaction
Madhumitha Venkatesan, Shicheng Wen, Jiajing Guo, Jorge Piazentin Ono, Liu Ren, Dongyu Liu
cs.AI
Graphical user interface (GUI) automation remains challenging in real-world environments, where dynamic layouts, unexpected dialogs, and evolving interface states can cause autonomous agents to drift from user intent. Recent vision-based multimodal agents improve flexibility by operating directly over screenshots and natural language instructions, but planning and adaptation often remain internal, limiting users' ability to inspect,...
-
08
Can We Trust Item Response Theory for AI Evaluation?
Han Jiang, Sunbeom Kwon, Jinwen Luo, Ziang Xiao, Susu Zhang
cs.AI
AI benchmarks increasingly leverage item-level statistical models, particularly item response theory (IRT), to estimate model capabilities, rank systems, select informative examples, and diagnose benchmark quality. However, AI benchmark data often departs from the data regime of human testing, for which standard IRT estimation tools were originally developed: benchmarks typically involve fewer evaluated models, far more items, and capability...
-
09
Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy
Patrick Phuoc Do, Chau M. Ta, Chaoli Wang
cs.AI · cs.CL · cs.HC
Multimodal large language models (MLLMs) are increasingly used to interpret visualizations, yet current evaluations remain largely chart-centric and provide limited evidence of understanding of scientific visualization (SciVis). We benchmark six MLLMs on the scientific visualization literacy assessment test, a standardized SciVis literacy assessment comprising 49 items based on 18 scientific visualizations and illustrations, spanning 8...
-
10
MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection
Goktug Ozkan
cs.AI · cs.CL
Most medical AI benchmarks measure whether a model knows the correct answer. MedFailBench asks a different question: which safety boundary failed? We present a clinician-built synthetic benchmark and failure atlas that labels medical AI errors by severity (1--5) and safety gate type (missed urgent escalation, unsafe remote dosing, unsafe discharge reassurance, evidence fabrication, unsafe protocol execution, source support gap). The current...
-
11
The Industrialization of Research ; On AI-Driven Science and Its Consequences
Emmanuel Jeannot
cs.AI · cs.CY
Artificial intelligence is transforming scientific research -- not merely as a more powerful instrument, but as an autonomous participant in the research cycle itself. This transition constitutes, in the most precise sense of the term, the industrialization of research: a shift from a craft model, in which knowledge, method, and judgment are embedded in the researcher, to a pipeline model, in which these steps are decomposed, automated, and...
-
12
Concept-Guided Spatial Regularization for World Models in Atari Pong
Yukuan Lu, Zaishuo Xia, Weyl Lu, Yubei Chen
cs.AI · cs.LG
World models are usually evaluated as components of model-based reinforcement learning (MBRL) systems, while the world models themselves are rarely studied in isolation. We examine five representative visual world-model agents in Atari Pong: DreamerV3, DIAMOND, TWISTER, Simulus, and STORM. After reproducing their training pipelines and matching the reported agent performance, we freeze the learned world models and evaluate them with a...
-
13
Long-Context Fine-Tuning with Limited VRAM
Vladimir Fedosov, Aleksandr Sazhin, Artemiy Grinenko, Frank Woernle
cs.AI
Parameter-efficient fine-tuning reduces model and optimizer memory, but dense attention still makes long training sequences expensive. We combine Hierarchical Global Attention (HGA) with segment-wise backpropagation and tiered KV storage. Only the active segment remains differentiable in VRAM; older KV is detached into RAM or NVMe, and HGA loads a bounded set of exact historical tokens for each query block. On Qwen3-8B with 4-bit QLoRA and...
-
14
BrainPilot: Automating Brain Discovery with Agentic Research
Haoxuan Li, Tianci Gao, Jianhe Li, Yang Fan, Runze Shi, Weiran Wang, Tianxiang Zhao, Zezhao Wu, Xiaoyang Jiang,...
cs.AI
Understanding the brain increasingly depends on integrating evidence across scales, modalities, and disciplines. Addressing a single research question therefore requires a coordinated sequence of operations, from surveying prior work to executing analyses and interpreting results in light of domain knowledge. AI agents promise to accelerate this process, but current agents lack domain expertise in brain science, may fabricate claims, drift...
-
15
Man, Machine, and Masterpiece: Artistic Ownership in the AI Era
Sofi Gjing Jovanovska, Kuntal Ghosh, Daniel Muhu Njenga, Ahmed Mufassir, Shadan Sadeghian
cs.AI
The integration of AI-driven systems in creative work has sparked debates among artists and legal communities about notions of ownership. Yet there remains little consensus on how ownership should be defined and attributed when human and AI contributions are intertwined. To provoke critical reflection on these tensions, we designed ArtSplit, a provotype that explicitly quantifies human and AI contributions across different stages of creative...
-
16
SMC-ES: Automated synthesis of formally verified control policies
Riccardo Curcio, Toni Mancini, Enrico Tronci
cs.AI · cs.LG · cs.NE
The deployment of autonomous cyber-physical systems in safety-critical environments requires closed-loop control strategies (i.e., policies) that are not only performant but also provably safe and robust. While learning-based methodologies such as Reinforcement Learning offer flexible and scalable approaches to automatically synthesize such controllers, they typically lack the formal guarantees necessary for safe deployment. To bridge this...
-
17
Moral Attitudes of Sentient ASI towards Humanity and Implications for AGI Development
Jean-Paul Van Belle
cs.AI · cs.CY
This paper suggests the adoption of a novel inversion in AI ethics: instead of asking how humans should treat artificial superintelligence (ASI), it examines how future sentient ASI may morally consider and evaluate humanity. We are not only designing intelligent systems but also shaping the initial conditions under which those systems form judgments about us. The paper proposes a preliminary set of post-human moral principles that may govern...
-
18
Demographically-Conditioned Synthetic Medical Images for Bias Mitigation and Bias Detection in Disease Classifiers
Mahmoud Ibrahim, Bart Elen, Chang Sun, Gokhan Ertaylan, Michel Dumontier
cs.AI
Per-subgroup fairness audits of medical image classifiers face a sample-size problem: minority subgroups in held-out test sets have so few samples that the resulting confidence intervals on per-subgroup performance are wider than the bias the audit is meant to detect. We argue that a demographically-conditioned synthetic generator can do both: mitigate bias on the training side and detect bias on the evaluation side. Working on COVID-19 chest...
-
19
CFM-Bench: A Unified Multi-Domain, Multi-Task Benchmark for Channel Foundation Models
Yuan Gao, Wenjun Yu, Jun Jiang, Yunfan Li, Xinyu Guo, Shugong Xu
cs.AI
Channel foundation models (CFMs) are developing rapidly, with recent studies reporting benefits from pretraining across downstream wireless tasks. Yet CFMs are commonly evaluated in model-specific pipelines with different data, radio configurations, partitions, adaptation procedures, task definitions, and metrics. Reported comparisons therefore tend to show that pretraining improves over supervised training from scratch within one pipeline,...
-
20
Explaining Process Control Optimisation Recommendations via GradientSHAP and Implicit Differentiation
Paul Darm, Cem Alpturk, Kenneth Ulrich, William Duncan, Ali Anwar, Annalisa Riccardi
cs.AI
Automated optimisation is increasingly adopted in industrial processes, yet a trust gap persists between engineers who design these algorithms and operators who must act on their recommendations. Explainable AI methods like SHAP (SHapley Additive exPlanations) have transformed interpretability for machine learning predictions; optimisation outputs could benefit from similar techniques. We present an approach that integrates Implicit Function...
-
21
Contextualized Early Detection of Online Firestorms: A Sequential LLM-Based Approach
Besim Shala, Peter Mandl, Andreas Humpe, Martin Häusl
cs.AI
Online firestorms are rapid collective escalations of highly negative user-generated content and may cause substantial reputational and economic damage. Existing detectors usually work with volume signals, sentiment scores, or predefined linguistic features. Such signals are useful, but they capture contextual meaning shifts in evolving discussion threads only indirectly. This paper proposes an LLM-based detection system with two operating...
-
22
Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Control
Jek Huang, Jeffery Hsia, Jiayi Sun, Freddie Shi, Wei Huang, Ian H. White
cs.AI · cs.SE
Autonomous coding agents increasingly execute multi-step software work, but lifecycle states such as reviewed, tested, DONE, and ready-to-merge remain claims unless supported by current evidence. We present Proof-or-Stop Lifecycle Control, a method that permits lifecycle transitions only when fresh, tracked-source-state-bound, mechanically verifiable evidence satisfies the relevant gate. The method treats agent outputs as claims rather than...
-
23
Reachability-Aware Pretraining for Efficient Target-Oriented Path Exploration in Temporal Knowledge Graph Reasoning
Chien-Liang Liu, Tsao-Lun Chen
cs.AI
Temporal Knowledge Graph (TKG) reasoning under the extrapolation setting focuses on forecasting future time-stamped events (facts) from historical data in a temporal knowledge graph. Existing approaches, reinforcement learning (RL)-based multi-hop reasoning methods are prominent for TKG reasoning because they produce human-interpretable predictions via explicit multi-hop path tracing. However, during RL training, rewards are typically sparse,...
-
24
CrimeNER Demo: Named-Entity Recognition in the Crime Domain
Miguel Lopez-Duran, Julian Fierrez, Aythami Morales, Daniel DeAlcala, Gonzalo Mancera, Javier Irigoyen, Ruben...
cs.AI
We present CrimeNER Demo, an AI-powered platform that enables us to extract general crime-related information from documents and classify them into entity types with two levels of granularity. We provide pretrained NER models on the CrimeNER database, and we give the possibility to users to provide their own annotated data to train models for their own specific cases. This demonstrator aims to promote crime-related NER research and provides a...
-
25
Transcoders for Investigating Deception in Language Models
Darius Lim, Nathan Leow, Xin Wei Chia
cs.AI
Transcoders have recently emerged as a promising approach for mechanistic interpretability (MI), enabling circuit-level analysis of model behaviour. In this paper, we investigate the use of transcoders to analyse deceptive behaviour in language models, a behaviour that poses a safety and security risk. Using a Qwen3-4B model with pre-trained transcoders, specifically per-layer transcoders (PLTs), we construct attribution graphs that capture...
-
26
Global Index on Responsible AI: 2026 Report
Rachel Adams, Fola Adeleke, Ayantola Alayande, Selamawit Engida Abdella, Ana Florido, Nicolás Grossman, Leah Junck
cs.AI
Grounded in human rights-based frameworks such as the UNESCO Recommendation on the Ethics of AI, the Global Index on Responsible AI (GIRAI) examines how countries translate responsible AI commitments into enforceable protections, institutional capacity, and redress mechanisms. GIRAI 2026 assesses these across five dimensions: Inclusion and Diversity, Ethics and Sustainability, Labour and Skills, Trust and Safety, and AI Use in Public Service....
-
27
AI vs Human Expert Reasoning: Assessing Agreements in Building Typology Predictions based on Street View Imagery
Zahratu Shabrina, Muhammad Asa, Jin Rui, Lu Yin, Stephen Law
cs.AI
This research investigates the potential of Vision-Language Models (VLMs) to infer building typologies: Construction, Current Use, and Storeys from Google Street View (GSV) images. Predictions generated by VLMs are compared with inference by human experts (civil engineers and architects) as a source of manually labelled ground-truth data. We evaluate several state-of-the-art VLMs, including GPT-4o, Claude 3.5 Sonnet, and Gemini 2.0 Flash. By...
-
28
InCarEmo: A Multimodal Dataset for In-Cabin Emotion Recognition and Driver State Monitoring
Hao Yang, Yanyan Zhao, Kewei Zhao, Hongbo Zhang, Tian Zheng, Yusheng Liu, Xing Fu, Bichen Wang, Yu Zhang, Hao He,...
cs.AI
Understanding driver emotion and state is critical for the next generation of intelligent in-cabin systems that ensure safety and enhance human-vehicle interaction. However, existing public datasets for in-cabin affective computing are largely limited to visual modalities and rarely include conversational information, making it difficult to capture the linguistic and interactive cues underlying driver emotion. To address these gaps, we...
-
29
Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment
Harikrishnan P M, Goutham Vignesh, Ganesh Parab, Saisubramaniam Gopalakrishnan, Vishal Vaddina, Varun V, Rohit Agrawal
cs.AI · cs.CL · cs.LG
Efficient multimodal document question answering with explicit visual grounding, locating the precise document region that supports each answer remains an open challenge. Current approaches bifurcate into Supervised Fine-Tuning (SFT), which requires large annotated datasets and reaches optimization plateaus, and reasoning-centric Reinforcement Learning (RL), which depends on verbose intermediate traces that inflate inference token cost...
-
30
Project Kaleidoscope: Contextual, Human-Aligned Evaluation for Real-World AI Applications
Leanne Tan, Rohan Jaggi, Shaun Khoo, Roy Ka-Wei Lee
cs.AI · cs.HC
Evaluations (Evals) are a deployment bottleneck for real-world AI applications: public benchmarks rarely match a team's users, context, or policies, and human review is often tedious to scale. Motivated by our work with AI applications in the public sector, this project addresses recurring evaluation challenges encountered when applications must satisfy local policy and governance requirements. We present Kaleidoscope, an integrated workflow...
-
31
SmartRAG: Native Graph-Based RAG for Mobile Device
Zhihan Jiang, Meng Li, Shenghao Liu, Keran Li, Ruiben Zhou, Xianjun Deng, Shuai Wang, Haipeng Dai
cs.AI
Deploying large language models (LLMs) as personal assistants on mobile devices demands privacy, low latency, and offline availability, yet the computational cost of giant models clashes with strict edge-hardware budgets. We argue that this tension cannot be resolved by model compression alone; it requires decomposing on-device intelligence into complementary functional roles. We present SmartRAG, a fully on-device framework that organizes an...
-
32
TopoAgent: A Self-Evolving Topological Agent for Multimodal Scientific Reasoning
Mingze Xu, Yinghui Li, Jiayi Kuang, Zhanhui Kang, Di Yin, Ying Shen, Xing Sun, Yuxing Han
cs.AI
While Multimodal Large Language Models (MLLMs) excel in general tasks, rigorous scientific reasoning remains challenging due to the limitations of monolithic, linear planning. Such sequential designs often suffer from visual-semantic misalignment, long-context hallucinations, and brittle execution under fixed task granularity. We propose TopoAgent, a self-evolving topological framework that replaces linear trajectories with dynamic,...
-
33
MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of MCP Servers
Huanxi Liu, Kun Hu, Jiaqi Liao, Qiang Wang, Pengfei Qian, YuanZhao Zhai, Dawei Feng, Bo Ding, Huaimin Wang
cs.AI · cs.SE
As Model Context Protocol (MCP) servers emerge as the core infrastructure for connecting LLMs with external tools, existing benchmarks leverage real-world MCP servers to evaluate LLM agents' tool-using capabilities. However, these benchmarks overlook the continuous evolution of tool interfaces and functionalities within MCP servers, resulting in flawed assessments that fail to capture the agent's adaptability in changing tool landscapes. To...
-
34
Analytic Abduction: Causal Decomposition and Governed Commitment for Human--AI Coordination
Remo Pareschi
cs.AI
Abductive reasoning operates in two directions. The synthetic mode builds explanations from available hypotheses; the analytic mode, conversely, identifies the latent factors whose interaction accounts for a complex observed state. This paper develops the analytic mode as a non-greedy, risk-sensitive discipline of commitment, in which candidate factors coexist and interact, resolving into committed conclusions only when explicit governance...
-
35
Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models
Yufeng Ji, Wenhao Tang, Haoyi Niu, Koushil Sreenath, Yi Wu, Zhongyu Li
cs.AI · cs.CV · cs.RO
Action supervision in vision-language-action (VLA) models is often treated as a downstream objective for learning action prediction. In this paper, we study it instead as a force that shapes inherited multimodal representations. We show that this shaping has a dual effect: it is necessary for forming action-compatible representations, but when action supervision is applied too directly to the inherited multimodal pathway, it can also...
-
36
SportD: Can VLMs Physically Strategize?
Jasin Cekinmez, Addison J. Wu, Haotian Xia, Akshaya Bharadhwaj, Anay Putty, Anirudh Ravishankar, Jaewoong Lee,...
cs.AI · cs.CV
Vision--language models have become increasingly capable of interpreting visual scenes, but it remains unclear whether they can use information to make strategically effective decisions. We investigate this question in soccer, where models observe the seconds preceding an on-ball decision and must choose whether to shoot or pass to a specific teammate. Unlike conventional visual-understanding tasks, soccer enables decisions to be evaluated...
-
37
MathCoPilot: An Interactive System for Human-AI Symbiotic Paradigm of Mathematical Research
Junjie Zhang, Jiayu Liu, Wenbin Liu, Zhenya Huang, Doudou Wang, Yan Jiang, Leiye Xu, Tao Xiong, Wen Huang, Qi Liu,...
cs.AI
Existing LLM-based theorem provers have achieved impressive results on formal mathematics benchmarks, yet they remain confined to acting as autonomous agents that prove a stated proposition. In this paper, we propose MathCoPilot, a human-in-the-loop system that embodies a new human--AI symbiotic paradigm for mathematical research, in which the mathematician steers the high-level mathematical direction while AI agents carry out the detailed...
-
38
Multi-LLM Collaborative MRI Report Generation for Visual Instruction Tuning in Brain Oncology
Sinyoung Ra, Jonghun Kim, Hyunjin Park
cs.AI · cs.CV
Recent advances in large language models (LLMs) and their extension to vision-language models (VLMs) have made it easier to combine text and images for tasks such as report generation. Existing VLMs in medicine typically focus on 2D images (chest X-rays), and their extension to 3D imaging has been difficult because of the lack of paired 3D imaging-text data. Thus, we introduce a new method for creating a 3D image-text dataset for brain...
-
39
Collaborative Spatial Learning with Multi-LLM Agents in Networked Social Experiments
Hao He, Chris J. Kuhlman, Xinwei Deng
cs.AI · cs.SI
Collective problem solving often requires that group members consider the tradeoff between exploitation of known solutions and exploration for new ones, where information of known solutions can be disseminated among individual members through communication networks. The Mason--Watts experiment (PNAS 2012) showed that human groups in shorter-path networks outperform those in longer-path networks on a two-dimensional search task. In this work,...
-
40
Alipay-PIBench: A Realistic Payment Integration Benchmark for Coding Agents
Shiyu Ying, Xuejie Cao, Yingfan Ma, Yuanhao Dong, Wenyu Chen, Bowen Song, Lin Zhu
cs.AI · cs.SE
Payment integration is a demanding repository-level software task: agents must select a suitable product, implement coordinated client-server flows, verify payment outcomes, and preserve consistency between transaction and business states. We introduce Alipay-PIBench, a benchmark for evaluating coding agents on realistic Alipay payment integration. It contains nine product-specific projects and 18 task instances, each organized into Basic...
-
41
Democratizing Agent Deployment Safety: A Structural Monitoring Approach
Preeti Ravindra, Rahul Tiwari, Vincent Wolowski
cs.AI · cs.CR
AI software development agents are increasingly capable of modifying infrastructure and security critical systems, creating risks where an agent completes its assigned task while covertly weakening safeguards through actions such as broadening permissions, degrading logging, or introducing persistence mechanisms. While frontier laboratories may deploy sophisticated monitoring pipelines, many organizations and individual users adopting coding...
-
42
Seeing the End at Step Zero: Accelerating Diffusion MLLMs via MLP Sparsity-Aware Truncation
Qicheng Zhao, Qi Sun, Zheyu Yan
cs.AI
Diffusion Multimodal Large Language Models (DMLLMs) are highly effective for multimodal reasoning, yet their inference efficiency is significantly hindered by fixed-length generation constraints. Since the actual output length is unknown, output sequences are padded to a predefined maximum length, resulting in substantial redundant computation over unnecessary [EOS] tokens. In this work, we discover that DMLLMs implicitly reveal their valid...
-
43
Towards an Intention Abstraction Layer for Autonomous Industrial Systems
Artan Markaj, Raphael Höfer, Felix Gehlhoff
cs.AI · cs.MA
Modern industrial environments increasingly run many autonomous subsystems at once - schedulers, energy managers, vehicle fleets - each pursuing its own goals while sharing the same physical resources. Because high-level human intentions are translated into low-level control logic and then discarded, no running component can tell whether it is still doing what was actually intended, and goal conflicts surface only after they have caused a...
-
44
Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent
Lingyun Yang, Yuxiao Wang, Shenghao Liang, Linfeng Yang, Daocheng Ying, Chunbo You, Rui Zhang, Luping Wang, Yinghao...
cs.AI
Existing GPU kernel generation benchmarks draw problems from synthetic or curated sources that diverge from deployed workloads. We present Atrex-Bench, a benchmark whose 30 operators and 440 shapes are sampled directly from full-cluster production inference traces of compute-limited, memory-rich GPUs. Each problem carries an importance weight derived from its share of observed GPU time, weighted by application card-hours and computed...
-
45
WrAFT: a Modularized Automated Writing Evaluation System for Argumentative Essays
Adnan Labib, Yixuan Huang, Jiahui Wu, John Maurice Gayed, Zheng Yuan, Qiao Wang
cs.AI · cs.CL
This study presents WrAFT, a Writing Assessment and Feedback Tool, that delivers both accurate and reliable scores and effective comprehensive feedback to argumentative essays. WrAFT adopts a modular design by dividing automated writing evaluation (AWE) tasks into scoring, surface-level feedback, and deep-level feedback. In building the system, various Large Language Models (LLMs) have been evaluated, including LLaMA-3.3-70B-Instruct, GPT-4o,...
-
46
RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning
Yanqiao Zhu, Jingru Gan, Xiaoqi Sun, Fang Sun, Yidan Shi, Md Mofijul Islam, Chao Shang, Wenhao Gao, Connor W. Coley,...
cs.AI · cs.CL · cs.LG
Multi-step retrosynthesis planning seeks to decompose a target molecule into commercially available building blocks through a sequence of feasible reactions. The vast combinatorial search space makes this task challenging even for expert chemists. Traditional methods combine tree search with offline-trained value networks that score candidates in isolation, without reasoning about complete multi-step routes. Recent work leverages Large...
-
47
VLT: A Vision-Language-Time Series Multimodal Foundation Model for Industrial Intelligence
Haiteng Wang, Jingheng Yan, Xiaokang Wang, Lei Ren
cs.AI
Industrial time series serve as the foundation for Prognostics and Health Management (PHM) to ensure the reliability and safety of industrial equipment such as aero-engines. However, existing approaches are typically limited to single-modality modeling, which restricts their generalization in complex scenarios. Although recent advances in large language models (LLMs) provide new opportunities for multimodal learning, bridging continuous...
-
48
Contextualized Evaluation of Vision Language Models through Dynamic, Multi-turn Interactions
Yijiang Li, Huiqi Zou, Bingyang Wang, Ziang Xiao
cs.AI
Multi-modal Large Language Models (MLLMs) have made substantial advances on benchmarks, yet their real-world effectiveness remains uncertain. This gap stems from the fundamental misalignment between benchmarks in controlled, static settings and the dynamic, interactive, and contextualized nature of real-world applications. To bridge this gap, we propose CEDI (Contextualized Evaluations of MLLMs through Dynamic, multi-round Interactions), a...
-
49
SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation
Yiming Zhang, Koji Tsuda
cs.AI · cs.IR · cs.LG
Complex knowledge base question answering (KBQA) is commonly approached through either information retrieval over a question-specific subgraph or semantic parsing into an executable logical form. We study the latter paradigm. Recent large language model agents make semantic parsing interactive: they alternate between reasoning, querying the knowledge base, and extending a partial SPARQL query. This interleaving reduces reliance on one-shot...
-
50
Step-Level Preference Learning for Generative Agents in Social Simulations
Wenchang Gao, Pingyue Sheng, Lanlan Qiu, Yunfei Ma, Jian Zhao, Baicheng Chen, Kangda Wang, Yuyang Tian, Shunqiang...
cs.AI
Large language model (LLM)-based generative agents simulate human behavior through long-horizon decision-making processes that comprise intermediate steps such as planning, memory retrieval, reflection, and action selection. However, fine-grained human annotations of these intermediate steps remain scarce, and existing agents are not grounded in human preferences over such intermediate decisions. To address this gap, we introduce \method, an...
-
51
Tactile: Giving Computer-Using Agents Hands and Feet
Yong Liu, Zhenyi Zhong, Zhanpeng Shi
cs.AI
Computer-use agents are becoming capable software operators, but their interface to desktop applications is still often a brittle motor layer: they look at screenshots, predict coordinates, click, and hope that the visible state changed as intended. This collapses target grounding, action execution, and outcome verification into a single ambiguous operation. We present Tactile, an open-source tool layer that gives agents a more reliable...
-
52
Per-Token Fixed-Point Convergence in Depth-Recurrent Transformers
Joe Logan
cs.AI
A depth-recurrent transformer applies a weight-tied core a variable number of times, and prior work has shown that training with a randomized recursion count yields one checkpoint usable across a range of inference depths. We ask what such a model actually computes per token, and measure it directly. On a 135M-class model trained on FineWeb-Edu, the recurrent state converges to a per-token fixed point: mean successive-output KL divergence...
-
53
CausalGraphX: A Counterfactual Graph Neural Network Framework for Explainable Systemic Risk Assessment
Rabimba Karanjai, Hemanth Madhavarao, Lei Xu, Weidong Shi
cs.AI
The interconnected nature of global financial systems makes them vulnerable to systemic risks, where the failure of a few institutions can trigger catastrophic cascading defaults. Traditional risk models often fail to capture the complex, non-linear dynamics of these networks. While Graph Neural Networks (GNNs) have shown promise in modeling relational data, they primarily learn correlative patterns and function as black boxes, offering...
-
54
Reward-Free Evolving Agents via Pairwise Validator
Minghao Liu, Yu Wang, Jiayun Wang, Wei Wei
cs.AI
A self-evolving agentic loop repeatedly proposes a tweaked version of an agent (its prompt template or program) and accepts or rejects the change based on a per-iteration quality signal. Designing that signal is often the costly part of the project: a reliable scalar reward requires domain expertise and labeled examples that are themselves as expensive to assemble as the agent's underlying task. We propose replacing the scalar at the...
-
55
Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration
Justin Bronder
cs.AI · cs.CL
Evaluations of language-model honesty read the model's verdicts as evidence about the model. We test the instrument instead. We built a text-adventure world where the game engine, not any model, knows whether the quest can be completed. A language model plays under a budget and must eventually declare its quest complete, unreachable, or not yet decidable; the engine scores every verdict. Decision rules were recorded before results were read,...
-
56
CatalogAgent: A Supervisor-mediated Self-Learning System Enabling Context Engineering for GenAI Models
Zhu Cheng, Zhenming Wang, Yu, Tang, Dan Liu, Bryan Zhang, Athanasios N. Nikolakopoulos, Pranav Souri Itabada, Jing...
cs.AI · cs.LG
Product catalogs are the backbone of e-commerce sites, yet a large number of structured attributes (SAs) -- such as material, color, and shape -- often have missing values. Typically, SA values are extracted from product information, including titles and descriptions. While LLM-based generator-evaluator frameworks have demonstrated effectiveness for SA prediction -- where an LLM generates SA values and another evaluates them -- they face...
-
57
A Comparative Analysis of Machine Learning Models for Long and Short-Term Forecasting of the Egyptian Stock Market: A Focus on EGX30
Muhammed Walid, Ahmed El-Naeimy, Hosam Moubarak, Walid Gomaa
cs.AI
This study concentrates on predicting stock prices in the Egyptian market, focusing on the EGX30, an influential financial hub in the Middle East. While most research focuses on global stocks, there's a growing need to understand stock trends in developing countries like Egypt. The study compares different machine learning models for forecasting EGX30 trends, covering short and long-term predictions. Using historical EGX30 data, including...
-
58
Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving
Yuan Gao, Wenting Miao, Mattia Piccinini, Haoyu Wang, Qunying Song, Johannes Betz
cs.AI · cs.RO
Validating autonomous driving systems requires diverse, regulation-compliant test scenarios. In simulation-based testing, scenarios are defined as executable scripts. Yet automatically generating such scripts from regulatory descriptions remains an open challenge, and existing approaches face fundamental trade-offs. Retrieval-assemble methods achieve reasonable compilation rates but lack scalability, whereas retrieval-based full-script...
-
59
CIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science Agents
Maxime Heuillet, Sharadind Peddiraju
cs.AI
Data science tasks span from closed-ended information extraction to open-ended analysis, presenting significant challenges for automation. Recent AI agents powered by language models show promise for handling such complex tasks. However, existing agents typically rely on a single initial state that conditions the entire agent's execution, making them vulnerable to cascading errors initiated by a suboptimal initial state. To mitigate this, we...
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.