cs.AI · 2026-07-14 · No. 53
Artificial Intelligence, 2026-07-14.
39 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
39 entries-
01
Playful AI in Professional Email: A Field Experiment on Tone and Recipient Engagement
Ziv Ben-Zion, Teddy Lazebnik
cs.AI · cs.HC
Large language models (LLMs) are rapidly reshaping workplace communication, yet whether AI-assisted writing changes how recipients actually behave, and through what channel, remains unknown. Here, in a randomized crossover field experiment, 121 employees across six companies sent work emails under three conditions over three weeks: unaided writing, GPT-5 rewriting in a playful tone, and GPT-5 rewriting in a professional tone. Across 16,880...
-
02
Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction
Huan Zhu
cs.AI
Self-refinement often fails to strengthen few-shot inductive reasoning in large language models. Prompting a model to explicitly state its inferred rule does little on its own. What actually matters is a structurally enforced isolation between reasoning stages, so that information can only pass between them as a compressed symbolic state. We introduce \textbf{Hourglass reasoning}, which enforces strict context isolation between reasoning...
-
03
Reproducing human biases in route choice using large language models: Toward scalable behavioral modeling
Jiangtao Han, Shoufeng Ma, Shuxian Xu, Geng Li, Shuai Ling, Ning Jia, Zhengbing He
cs.AI · cs.CL · cs.LG · cs.SI · physics.soc-ph
Human choice behavior, including route choice, exhibits systematic behavioral biases that deviate from the assumptions of full rationality. Cumulative prospect theory (CPT) has been widely recognized as an effective framework for characterizing such behavioral patterns. However, its large-scale application, particularly in simulation and agent-based modeling, critically depends on specifying individual-level CPT parameters, which remain a...
-
04
Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns
Yong Yang, Xiang Guan, Sophie Arheix-Parras, Saeed Ahmadi, Roger Newman-Norlund, Leonardo Bonilha, Christopher...
cs.AI · cs.CL · cs.LG
Aphasia following stroke commonly produces systematic naming errors with characteristic profiles, but whether general-purpose language models not designed for clinical simulation can reproduce these patterns remains untested. We investigated (1) whether lesions or controlled perturbations to a multimodal language model can reproduce different types of errors in picture naming, and (2) whether the framework can reproduce the complete error...
-
05
Auditing the Risk Claims of Distributional Reinforcement Learning
Hari Prasad
cs.AI · cs.LG · stat.ML
Distributional reinforcement learning agents learn full return distributions that are increasingly read at face value: for interpretability, risk-sensitive control, and safety monitoring. We ask a question theory anticipates but that has not been measured directly: are the risk claims of a trained distributional agent true? Our audit combines a decision-relevant screening metric (the excess Wasserstein gap between the top two actions, which...
-
06
Interaction Scaling: Grounding the Third Axis of Test-Time Compute
Bojie Li, Noah Shi
cs.AI
There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one. Both share a hidden limit: they are internal. Every extra token comes from the same frozen weights and the same prompt, so neither can tell the model anything it does not already know. We study a third way, interaction: the model proposes an artifact, an external instrument observes how it actually behaves, and the...
-
07
MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models
Tsz Hei Fan, Choi Wing Fung, Yuxuan Wan, Shuqing Li, Michael R. Lyu
cs.AI · cs.GR
Multi-scene navigation (clearing an objective in one bounded space and then crossing a portal into the next) is a defining feature of contemporary 3D games, but authoring it is laborious: every portal must have consistent endpoints on both sides, each interior must remain navigable once it is furnished, and the resulting connectivity must be kept consistent across many files. Recent large language model (LLM) and multimodal LLM (MLLM) scene...
-
08
HCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference
Yongqin Zhang
cs.AI
Mixture-of-Experts (MoE) large language models (LLM) activate only a small number of experts during inference, but token routing introduces persistent expert hotness skew: a small set of hot experts continuously receives most tokens, while the remaining experts are lightly loaded. On 3.5D multi-chiplet systems, this skew not only causes compute imbalance but also amplifies pressure on communication, memory bandwidth, I/O, and execution...
-
09
Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning
Jiamian Li, Niall McShane, Attila Korik, Naomi du Bois, Karl McCreadie, Leen Jabban, Benjamin Metcalfe, Özgür...
cs.AI · cs.LG
Decoding continuous three-dimensional (3D) motor imagery (MI) using non-invasive electroencephalography (EEG)-based brain--computer interfaces (BCIs) remains challenging due to signal variability and residual decoding errors. Deep learning architectures such as convolutional neural network--long short-term memory (CNN--LSTM) models can capture spatial and temporal dynamics for continuous kinematic decoding; however, systematic residual errors...
-
10
Comparative Analysis of GAT and BERT for Human-Like Playtesting
Kleio Fragkedaki, Theodoros Panagiotakopoulos, Matteo Biasielli, Hui Wang
cs.AI
Accurately modeling and understanding player experience is crucial for designing engaging puzzle games. To achieve this, a common approach involves collecting diverse user data to train predictive playtesting models that mimic player behavior. However, existing data-driven methods often lack the ability to capture the full range of player strategies and require extensive feature engineering and network architecture modeling. This limitation...
-
11
Enhancing Query Efficiency for d-DNNF Representations Through Preprocessing
Jean Marie Lagniez, Emmanuel Lonca
cs.AI
In this paper, we investigate preprocessing techniques aimed at improving the efficiency of accessing models of propositional formulas represented in conjunctive normal form (CNF). We focus on three fundamental tasks: uniform sampling, direct model access, and model enumeration. Our analysis reveals that most state-of-the-art preprocessors, when they do not preserve formula equivalence, are generally unsuitable for these tasks. In contrast,...
-
12
The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning
Wencheng Ye, Yi Bin, Yujuan Ding, Hongye Fang, Zheng Wang, Xing Xu, Jingkuan Song, Yun Zhang, Sirui Da, Heng Tao Shen
cs.AI
Vision-language models increasingly succeed on multimodal reasoning benchmarks, yet their visual evidence often becomes unstable once it enters the language stack, weakening evidence-grounded reasoning. To understand this fragility, we examine the internal dynamics of VLMs through a mechanistic lens and uncover a stable three-stage redistribution of multimodal attention focus across depth: an early question-conditioned organization, a...
-
13
Omni-Decision: A Progressive Evidence-State Agent System for Omni-Modal QA
Ming Ma, Yi Zhu, Yiran Zhong, Feida Zhu, Weigao Sun, Junhan Shi, Lingrui Mei, Tianming Yang, Steven Hoi
cs.AI
Omni-modal evidence-seeking QA requires agents to answer questions whose evidence is sparsely distributed across videos, audio, images, web pages, and computation results. Existing agentic multimodal systems often leave evidence in scratchpads, tool trajectories, or free-form histories, making it difficult to track what has been grounded, what remains missing, and when the evidence is sufficient to answer. We propose Omni-Decision, a...
-
14
StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure
Wenyi Wu, Sibo Zhu, Kun Zhou, Aayush Salvi, Zixuan Song, Biwei Huang
cs.AI · cs.CL · cs.LG · cs.MA
Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled increasingly capable digital agents for computer use. However, real-world tasks are often long-horizon and involve evolving contexts containing accumulated observations, intermediate edits, failed attempts, and partially completed executions. Existing agents typically operate over raw interaction history, making task progress difficult to interpret,...
-
15
OpsMem: Dual-Memory Reasoning with Cross-Memory Resonance for Failure Diagnosis
Yongqian Sun, Rongchen Gao, Yu Luo, Wenwei Gu, Shenglin Zhang, Qingyi Guo, Qiuai Fu, Yaoliang Wu, Dan Pei
cs.AI · cs.SE
Failure diagnosis in modern software systems requires iterative evidence acquisition and hypothesis reasoning guided by operational experience. Existing LLM-based methods improve diagnosis through agentic reasoning or knowledge augmentation, but they often lack a mechanism to coordinate the evolving diagnostic state with operational experience during iterative diagnosis. We propose OpsMem, a dual-memory framework that maintains a short-term...
-
16
From Neural Network Decisions to Training Cases: An Exact Account via Case-Based Decision Theory
Manli Yan, Yuebin Lin, Yaowen Yu, Yong Zhao
cs.AI
Neural networks increasingly guide decisions in high-stakes domains such as medical diagnosis, credit approval, and energy bidding. Audit in these settings requires case-level evidence: which training cases support an action and what outcomes they carried. Case-based decision theory (CBDT) formalizes this reasoning by aggregating outcome support from remembered cases. We show that an OLS action readout fitted on a fixed neural representation...
-
17
Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents
Chenglin Yu, Li Yin, Ying Yu, Hongxia Yang, Ming Li
cs.AI · cs.PL
Enterprise agents must follow long-horizon, conditional, safety-critical standard operating procedures (SOPs). We compile machine-readable SOP constraints into executable pseudo-code and run them with a program-guided (PG) stack machine that pages the active frame while an LLM performs semantic execution. A three-arm SOPBench study across six models separates representation from runtime: compiled text never significantly hurts and gains up to...
-
18
AutoVSR: Automatic Visual-to-Symbolic Reasoning for Symbolic Expression Generation from Circuit Schematic
Zhe Xiao, Longfei Li, Xu He, Haoying Wu, Zixing Zhang, Mingyu Liu
cs.AI
Symbolic expressions can effectively characterize and predict circuit behavior, but deriving them directly from circuit schematics is challenging. This process requires accurate visual-to-symbolic construction of circuit structure from images and correct multi-step symbolic derivation, both of which impose strict correctness requirements. This work proposes AutoVSR, an automated framework for visual-to-symbolic generation of circuit...
-
19
Verifier-Guided Twelve-Tone Composition: A Generate-Verify-Repair Harness for Symbolic Music Generation
Congren Dai, Danni Zhao, Enyang Liu, Michael Ching Yam, Zhancheng Guo, Siyi Gu, Wentao Yang, Bo Dai, Xiaobing Li, Maosong Sun
cs.AI
Large language models can produce superficially legal twelve-tone scores that collapse into degenerate textures. We introduce a neuro-symbolic harness that wraps a language-model proposer in a generate-verify-repair-trace loop with symbolic verification. The complete pipeline improves event-local consistency without claiming whole-piece legality. Across 40 controlled tasks and four paired models, audited delivery yield rises from 13.3% under...
-
20
Calibrated e-CUSUM Decoding for Quantized Reasoning Models: Why Token Log-Probability Is the Wrong Observable for Decoding Monitors
El Hassane Ettifouri, Ayoub Belfatmi, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane
cs.AI · cs.IT
Low-bit quantization makes small reasoning models inexpensive to deploy but can degrade their chains of thought. This motivates decoder-side monitors that intervene when generation becomes unreliable. We show that a natural candidate, the centered token log-probability increment $\log p(w_t)+H_t$, is the wrong observable for this purpose. Under the model's own sampling law it is a mean-zero martingale by construction, so it measures sampling...
-
21
Efficient Test-Time Optimization for Multi-Agent Proof Autoformalization
Tian-Shuo Liu, Shiyuan Zhang, Zijie Geng, Haoyu Liu, Runjie Xu, Pengyuan Wang, Lei Yuan, Yang Yu
cs.AI
Full-proof autoformalization bridges extensive mathematical proofs in natural language with formally validated reasoning, offering a pathway to elevate the ceiling of verifiable mathematical reasoning. Unlike statement-level formalization, proof autoformalization is a long-horizon challenge requiring coordination of claims, contexts, and dependencies across many proof steps, yet has only recently come under focused study. Current approaches...
-
22
Valid $\ne$ Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought
Daeyeop Lee, Hwanjo Yu
cs.AI
Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs), yet it often incurs substantial computational costs due to over-reasoning: the generation of redundant, verbose, or irrelevant steps. While existing reasoning step evaluators effectively detect logical fallacies and factual errors, our analysis reveals a critical blind spot: they fail to penalize valid but inefficient...
-
23
Bringing Back Rule Induction to Fluid Intelligence Research? An Initial Validation of the ARC-AGI Benchmark in Humans
Jasmin Thelen, Oliver Wilhelm
cs.AI · cs.LG
Two competing perspectives on fluid intelligence (gf) measures propose that performance is primarily constrained either by working memory capacity or by the ability to induce novel relations. The first perspective is currently dominant in measurement, as evident from the use of a limited set of recurring rules, whereas the second perspective is reflected in many definitions but rarely present in measurement. The ARC-AGI benchmark...
-
24
Heterogeneous Agent Cohorts for Safe Open-Ended Exploration with Runtime Constraint Memory
Tengjiao Liu
cs.AI
LLM agents today are caught in an awkward bind. Lock them down with static safety instructions and they rarely venture beyond the obvious; give them free reign with tools and multi-agent debate, and safety violations quickly follow. Rather than forcing a single model to juggle both creativity and caution, we separate the concerns across specialized roles. A Disrupter generates unconventional proposals, a Validator enforces hard runtime checks...
-
25
PREF-Gate: Provenance-Constrained Relational Evidence Fusion with Validation-Gated Selection for Graph Fraud Detection
Liming Liu, Chao Hu, Mingfei Lu, Yiwei Ge, Xingle Li, Heyuan Shi
cs.AI · cs.LG
Relational fraud detection can exploit both label-free graph context and label-derived neighborhood evidence, but these two information sources obey different validity conditions. In particular, neighborhood risk becomes invalid when a queried node's own label, or any validation or test label, enters its construction. We formulate this issue as provenance-constrained relational evidence use and present PREF-Gate, an auditable decision...
-
26
What We Talk About When We Talk About LLM Planning: Evidence for Two Distinct Planning Abilities
Sukai Huang, Chenyuan Zhang, Fucai Ke, Zhixi Cai, Naim Rastgoo, Gholamreza Haffari, Hamid Rezatofighi
cs.AI
When LLMs exhibit uneven performance across planning tasks, these gaps are often attributed to task difficulty. We argue that this explanation is incomplete, as task-level variation may reflect distinct latent planning competencies rather than differences along a single ability spectrum. We study this question on ACPBench-Hard by evaluating multiple LLM families under varying test-time reasoning budgets and applying a multidimensional item...
-
27
SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL
Bowen Lv, Xiao Liu, Yanyu Ren, Hanyu Lai, Bohao Jing, Hanchen Zhang, Yanxiao Zhao, Shuntian Yao, Jie Tang, Yuxiao Dong
cs.AI
Computer use agents (CUAs) are emerging as a powerful interface for automating complex digital workflows through visual perception and GUI execution. Online reinforcement learning with verifiable rewards (RLVR) has emerged as a key direction for scaling their capabilities. However, this paradigm is bottlenecked by verifiable data scarcity and online RL inefficiency. To break these barriers, we introduce ScaleCUA, a unified framework that...
-
28
The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy
Chunzheng Zhu, Lei Tian, Bohan Tan, Ziqi Zhou, Yuxuan Sun, Yijun Wang, Chengchao Lv, Yilin Wen, Yijun He, Jinghao...
cs.AI
The growing ability of large language models and vision language models to jointly interpret and reason over images and text is reshaping medical agents, moving them from task specific predictors toward autonomous systems that perceive, reason, plan, remember, and act in clinical environments. This work departs from the capability first perspective of existing literature and instead begins from clinical deployment, asking what tasks,...
-
29
STAMP: Provenance-Guided Credit Assignment for Deep Search Agents
Ke Xu, Han Xu, Xinran Chen, Yuqian Wang, Zhixuan Li, Xiaojian Liu, Changwo Wu, Jianqiang Xia, Yuchen Li
cs.AI · cs.LG
Reinforcement learning for deep-search agents has largely focused on trajectory-level scoring -- outcome correctness, citation-aware rewards, and evidence coverage. Yet the actions that expose supporting documents receive no targeted credit, a gap we call the reward-credit mismatch. We propose STAMP, in which a reference-based verifier judges whether each cited document supports an entity or relation in a training-time evidence graph, and...
-
30
The Hidden Footprint: Making Storage a First-Class Metric for LLM Agent Evaluation
Chenglin Yu, Hongquan Gui, Ying Yu, Hongxia Yang, Ming Li
cs.AI
LLM agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an agent run leaves on disk, including logs, context snapshots, checkpoints, and debug traces. We introduce AgentFootprint, a cross-framework benchmark of post-run agent storage footprint. Its serialization-aware metric suite measures total retention, channel composition, duplication, growth, compressibility, and conversation-history...
-
31
NextFund: A Unified Performance Tracking Platform for Agentic Portfolio Management
Changlun Li, Peixian Ma, Qiqi Duan, Zhenyu Lin, Peineng Wu
cs.AI
Large language models (LLMs) based agents are beginning to participate in portfolio construction and market analysis, where decisions must be justified under evolving information and risk constraints. Current assessment practice, however, remains poorly aligned with this setting: many studies rely on static examinations or report only terminal portfolio returns, while the intermediate evidence, analyst judgments, and execution steps that...
-
32
A Formal Hierarchical Architecture for Agentic Orchestration with Stack-Based Execution and Lazy Discovery
Prashant Devadiga, Abhishek, Adithya Mishra, Alok Singh, Amisha Sinha, Asit Desai, Gaurang Dahad, Harshit Bhushan,...
cs.AI · cs.LG
The rapid expansion of capabilities in Large Language Model (LLM) agents has exposed a critical architectural bottleneck: when agents are given access to a flat, monolithic registry of tools, the model must evaluate hundreds or thousands of options simultaneously. This leads to decision-space explosion, context window saturation, and degraded routing accuracy. To address these limitations, this paper presents a hierarchical, skill-based...
-
33
OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping
Mohammed Ehab, Aymane El Gadarri, Vivek F. Farias, Adam Jozefiak, Ciamac C. Moallemi
cs.AI
Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks through Chain-of-Thought (CoT) prompting. However, these models often exhibit "computational overthinking," generating redundant reasoning steps that increase latency and cost without improving accuracy. Recent studies suggest that CoT trajectories can be significantly pruned, yet existing methods often rely on forcing a static thinking budget, heuristic...
-
34
NVAITC AI Scientist: A Governed End-to-End Research System -- A Hypertension GWAS Case Study
Eddie Huang, Ken Liao, Iven Fu, Yang-Hsien Lin, Chao-Shun Zhan, Andy Liao, Virginia Chen, Johnson Sun, Pika Wang,...
cs.AI
Agentic research systems are emerging as a new paradigm for coordinating scientific workflows beyond isolated model inference, code generation, or statistical analysis. However, deployment in institutional biomedical environments requires governed mechanisms for research planning, data access, workflow orchestration, evidence tracking, reproducibility, and human oversight. We present NVAITC AI Scientist (NAIS), a governed end-to-end agentic...
-
35
Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists
Chuhan Shi, Xiaoquan Ren, Sicheng Song, Haobo Li, Rui Sheng, Yushi Sun
cs.AI
Existing benchmarks for scientific data analysis evaluate LLMs primarily on code execution or workflow completion, overlooking that scientific analysis serves to support distinct types of scientific claims: hypothesis exploration, statistical inference, mechanistic explanation, each with different assumptions and validity criteria. We introduce SDABench, a benchmark that reorganizes evaluation around six capabilities (descriptive,...
-
36
AdvNav: Behavior-Guided Black-Box Adversarial Attacks on Vision-Language Navigation
Chenyang Li, Kaige Li, Zeyu Jiang, Changhao Chen
cs.AI
Despite progress in Embodied AI, Vision-and-Language Navigation systems remain vulnerable to adversarial visual disturbances. Most existing methods rely on white-box access to target model gradients, which is often unrealistic for real-world deployed systems and computationally exhaustive due to recursive backpropagation for optimization, limiting their applicability. While previous black-box methods predominantly target single-step,...
-
37
QwenPaw-Data: Bridging Facts, Methodology, and Execution for Autonomous Enterprise Data Analytics
Tianjing Zeng, Yuntao Hong, Zhongjun Ding, Dandan Liu, Yinan Mei, Yunxiang Su, Yiming Wang, Xiaojian Zhang, Jingyu...
cs.AI
Enterprise data analysis is emerging as a distinct frontier for autonomous agents. Compared with general-purpose interaction and software engineering, it operates in an open, ambiguous, and continuously evolving environment. These characteristics call for a data-agent architecture that treats semantics, methodology, execution, and evolution as first-class system concerns. To this end, we introduce QwenPaw-Data, an agentic data system designed...
-
38
From Checker to Forecaster: Code-Owned Evaluation of Model-Generated Strategic Routes Under Delayed Ground Truth
Aleh Manchuliantsau
cs.AI
Many evaluations of model outputs rely either on contracts checkable at evaluation time or on feedback that arrives within the operating loop. We study the complementary setting in which ground truth is delayed, censored, or private, so deterministic code cannot check correctness at scoring time and must instead issue a code-owned provisional forecast. RouteCast instantiates this regime for model-generated typed strategic routes: models...
-
39
SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning
Mingyuan Wu, Jingcheng Yang, Shengyi Qian, Xudong Wang, Jize Jiang, Qifan Wang, Aashu Singh, Khoi Pham, Fei Liu,...
cs.AI
We introduce Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a learning signal for multimodal reasoning. For each query, the model proposes an answer using the same weights, and issues a binary self-verdict (Yes/No). A 'No' triggers a second-chance rethink; a 'Yes,' or a turn cap, finalizes the output for computing the outcome-based reward. SVR-R1 is implemented with GRPO and an...
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.