cs.AI · 2026-06-20 · No. 29
Artificial Intelligence, 2026-06-20.
41 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
41 entries-
01
Toward Calibrated Mixture-of-Experts Under Distribution Shift
Gina Wong, Drew Prinster, Suchi Saria, Rama Chellappa, Anqi Liu
cs.AI · cs.LG
Calibration aligns a model's predictive uncertainty with the frequencies of its empirical outcomes and is important for understanding and trusting reported probabilities. Recent work shows that enforcing calibration at the level of individual predictors can improve ensemble accuracy and calibration, with mixture-of-experts (MoE) models showing strong empirical improvements in particular; however, the conditions under which calibration helps...
-
02
How Do Instructions Shape Speech? Cross-Attention Attribution for Style-Captioned Text-to-Speech
Nityanand Mathur, Hamees Sayed, Wasim Madha, Apoorv Singh, Sameer Khurana, Akshat Mandloi, Sudarshan Kamath
cs.AI
Style-captioned text-to-speech systems use natural language to control voice characteristics, but how individual words influence acoustic output remains unclear. Understanding this is critical for diagnosing failure modes and improving controllability in expressive TTS. We propose cross-attention attribution for speech diffusion models, adapting the DAAM framework to the speech domain for the first time, and apply it to CapSpeech-TTS. Our...
-
03
LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents
Md Nayem Uddin, Amir Saeidi, Eduardo Blanco, Chitta Baral
cs.AI · cs.CL
Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies. Task states consist of relevant facts, identifiers, constraints, and conditions observed through user interaction and tool calls. In standard agents, task states are not represented separately. Observations, tool returns, and policy instructions are placed in the prompt, leaving agents to...
-
04
DeepSWIP: Quotient-WMC Counterfactuals for Neural Probabilistic Logic Programs
Saimun Habib, Vaishak Belle, Fengxiang He
cs.AI
Neurosymbolic systems such as DeepProbLog combine neural perception with probabilistic logic, but standard inference is associational. Counterfactual reasoning additionally requires a causal semantics for interventions and evidence. We introduce DeepSWIP, a single-world counterfactual semantics for DeepProbLog programs. Using neural materialization, we reduce fixed-context neural predicates to ordinary ProbLog choices, apply Single World...
-
05
FlowEdit: Associative Memory for Lifelong Pronunciation Adaptation in Flow-Matching TTS
Harshit Singh, Ayush Pratap Singh, Nityanand Mathur
cs.AI
Flow-matching text-to-speech systems achieve remarkable zero-shot quality but remain static after deployment: pronunciation errors on out-of-vocabulary proper nouns persist unless the model is retrained. We introduce FlowEdit, a life-long adaptation framework for frozen flow-matching TTS that learns pronunciation corrections as latent conditioning edits rather than weight updates. When corrective feedback is provided, FlowEdit optimizes a...
-
06
Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages
Maria Ivanova, Pavel Zadorozhny, Rodion Levichev, Ivan Petrov, Adamenko Pavel, Ivan Lopatin, Alexey Kutalev, Dmitrii Babaev
cs.AI · cs.PL
LiveCodeBench (LCB) has recently become a widely adopted benchmark for evaluating large language models (LLMs) on code-generation tasks. By curating competitive programming problems, constantly adding fresh problems to the set, and filtering them by release dates, LCB provides contamination-aware evaluation and offers a holistic view of coding capability. However, LCB remains restricted to Python, leaving open the question of whether LLMs can...
-
07
What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?
Sihui Dai, Mann Patel
cs.AI · cs.LG
Prior work has shown that in-context demonstrations can jailbreak language models, but it remains unclear how models interpret different types of compliance demonstrations. We study this by mixing benign compliance demonstrations (non-harmful request, helpful response) with harmful compliance demonstrations (harmful request, helpful response) and testing three hypotheses about how demonstration composition drives harmful compliance. Across...
-
08
Context-Aware Hierarchical Bayesian Modeling of IVF Laboratory Environmental Conditions
Zahra Asghari Varzaneh, Reza Khoshkangini, Pia Saldeen, Lars Johansson, Thomas Ebner
cs.AI
IVF pregnancy rates are routinely modeled using patient-level variables, while high-resolution laboratory environmental data remain underutilized. We show that this is a missed opportunity. Rather than relying on raw sensor averages, we engineer 55 context-aware temporal features, including rolling thermal stability, simultaneous temperature-humidity adherence, peak stress duration, and post-stress recovery speed, that capture the dynamics of...
-
09
Interpretable Sperm Morphology Classification via Attention-Guided Deep Learning
Zahra Asghari Varzaneh, Reza Khoshkangini, Thomas Ebner, Lars Johansson
cs.AI
Male infertility is a major cause of couple infertility, often linked to abnormal sperm morphology. While deep learning models offer automated analysis, most lack interpretability, limiting their clinical adoption. This study proposes an attention-guided deep learning framework for sperm morphology classification. We combine a pretrained EfficientNet-B0 with a Convolutional Block Attention Module (CBAM) to focus on key areas of the sperm...
-
10
Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 Recipe
Qian Zhao, Kunlong Chen, Changxin Tian, Zhonghui Jiang, Haitao Zhang, Chaofan Yu, Peijie Jiang, Mingliang Gong, Jia...
cs.AI
FP4 training promises substantial reductions in memory and computation cost for LLM pretraining, yet current FP4 hardware paths and recipes, including NVIDIA Blackwell/Rubin-class systems and AMD MI350-series GPUs, remain centered on E2M1 data elements. In this study, we identify a fundamental limitation of that choice: non-uniform formats such as E2M1 inherently suffer from Shrinkage Bias, a systematic negative rounding error caused by the...
-
11
Automating SKILL.md Generation for Computer-Using Agents via Interaction Trajectory Mining
Yuexing Hao, Xiaomin Li
cs.AI
Explicit skill libraries make computer-using agents easier to inspect, but it remains unclear whether such libraries can be mined from interaction data in a way that improves downstream policies. We study this question through a three-stage pipeline that segments GUI trajectories, clusters segments into candidate skills, and trains a skill-aware policy from the resulting annotations. The mined clusters are readable on the source benchmark:...
-
12
SoftSkill: Behavioral Compression for Contextual Adaptation
Xijia Tao, Yihua Teng, Xinyu Fu, Ziru Liu, Kecheng Chen, Yuzhi Zhao, Suiyun Zhang, Rui Liu, Lingpeng Kong
cs.AI
Agent skills are commonly deployed as natural-language Markdown files that encode answer policies, evidence-use habits, and task procedures. These files are readable and portable, but they are consumed indirectly: for each task instance, a frozen language model must translate a long textual artifact into generation-time behavior. This paper asks whether a natural-language skill can instead initialize a compact continuous context object,...
-
13
Leveraging systems' non-linearity to tackle the scarcity of data in the design of Intelligent Fault Diagnosis Systems
Giancarlo Santamato, Andrea Mattia Garavagno, Massimiliano Solazzi, Antonio Frisoli
cs.AI
Deep Transfer Learning (DTL) allows for the efficient building of Intelligent Fault Diagnosis Systems (IFDS). On the other hand, DTL methods still heavily rely on large amounts of labelled data. Obtaining such an amount of data can be challenging when dealing with machines or structures faults. This document proposes a novel approach to the design of vibration-based IFDS using DTL in condition of strong data scarcity. A periodic...
-
14
Lagrange: An Open-Vocabulary, Energy-Based Sparse Framework for Generalized End-to-End Driving
Shihao Ji, HongXi Li, Zihui Song, Mingyu Li
cs.AI
Scaling end-to-end autonomous driving to complex, open-world environments requires perceptual models that generalize to anomalous scenarios and planners that produce kinematically valid trajectories. Existing paradigms face a distinct dichotomy between representational efficiency and generalization capacity. Dense models (e.g., occupancy networks), while geometrically robust, incur critical computational bottlenecks and struggle with...
-
15
Confidence-Aware Automated Assessment of Student-Drawn Scientific Models
Luyang Fang, Yingchuan Zhang, Jongchan Park, Zhaoji Wang, Ping Ma, Xiaoming Zhai
cs.AI
Student-generated drawings are widely used in science education to assess learners' conceptual understanding in modeling-based tasks aligned with the Next Generation Science Standards (NGSS). However, scoring such drawings requires expert human judgment to interpret complex visual representations, making large-scale assessment costly to implement and sustain in classroom settings. In this work, we study automated scoring of student-generated...
-
16
Navigating Unreliable Parametric and Contextual Knowledge: Explicit Knowledge Conflict Resolution for LLM Inference
Huang Peng, Jiuyang Tang, Weixin Zeng, Hao Xu, Xiang Zhao
cs.AI
Large language models (LLMs) have achieved strong performance across a wide range of language-based tasks by leveraging both extensive parametric knowledge and in-context learning ability, enabling them to incorporate external information provided in the input prompt. However, the integration of external knowledge can introduce conflicts, not only between the model's internal parametric knowledge and the external information, but also among...
-
17
A Multi-Agent system for Multi-Objective constrained optimization
Federica Filippini
cs.AI · cs.LG · cs.MA
Many decision-making problems in computing and networking systems can be naturally formulated as cost-minimization problems under performance constraints. In dynamic environments, reinforcement learning (RL) is often used to solve such problems at runtime by embedding both costs and constraint violations into a single scalar reward through weighted penalty terms, following a Lagrangian-inspired formulation. However, in this context the...
-
18
Thermodynamic Measure of Intelligence
Ishanu Chattopadhyay
cs.AI · cond-mat.stat-mech · cs.IT · math-ph · nlin.AO
Can intelligence be measured? We propose that intelligence can be defined as the lawful amplification of rare but valid futures: a system increases the probability of outcomes that would be unlikely under passive dynamics but remain admissible under the constraints of the domain. We start with the premise that an intelligent system must model the world and its own place within it. Because the system is part of the world it models, this leads...
-
19
QMFOL: Benchmarking Large Language Model Reasoning via Quantifiable Monadic First-Order Logic Test Case Generation
Xinyi Zheng, Ling Shi, Tianlong Yu, Yongxin Zhao, Lorenz Goette, Kailong Wang
cs.AI · cs.SE
Large Language Models (LLMs) have made significant progress in reasoning, particularly in deductive reasoning, which is crucial for high-stakes decision-making. As models improve, evaluation benchmarks should evolve to keep pace. However, existing benchmarks lack fine-grained control over logical complexity and struggle to balance semantic diversity with logical consistency. To address these issues, we propose QMFOL, an automated framework...
-
20
Augmenting Game AI with Deep Reinforcement Learning
Alessandro Sestini, Joakim Bergdahl, Amir Baghi, Jean-Philippe Barrette-LaPierre, Florian Fuchs, Linus Gisslén
cs.AI
Immersion in video games depends not only on graphics, audio, and game mechanics, but also on the quality of in-game characters. Producing believable characters, or game AI, remains a significant challenge as behavioral complexity is hard to capture with hand-coded systems. Game AI is a source of immersion and engagement; however, the limitations stemming from the challenges of creating game AI often lead to frustration and the breaking of...
-
21
Beyond Accuracy: Measuring Logical Compliance of Predictive Models
Guillaume Olivier Delplanque, Pierre Genevès, Nabil Layaïda, Zephirin Faure
cs.AI · cs.DB · cs.NE
Machine learning models are predominantly evaluated through predictive performance metrics such as ranking quality, prediction error, or classification accuracy. While these metrics effectively quantify how closely predictions match the ground truth, they do not assess whether model outputs respect predefined logical or domain-specific constraints. In high-stakes applications, including healthcare, finance, and autonomous systems, logical...
-
22
Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact
Jelena Meyer, David Garcia, Dirk U. Wulff
cs.AI · cs.CL · cs.HC
Psychological instruments designed for humans are increasingly used to assign large language models (LLMs) stable psychological profiles that affect their usability, safety assessment, and use as proxies for human participants in research. Using a formal psychometric framework, we show that these profiles are largely a measurement artifact. Administering a battery of personality and risk-preference instruments spanning self-reports and...
-
23
Implicit Semantic-Aware Communication Based on Hypergraph Reasoning
Yiwei Liao, Shurui Tu, Yong Xiao, Yingyu Li, Guangming Shi
cs.AI · cs.IT · cs.NI
Semantic-aware communication has emerged as a transformative paradigm for next-generation communication systems, shifting the fundamental goal from transmitting bit-level symbols to reliably recovering and understanding the semantic meaning of information. Previous studies have demonstrated that representing the semantic content of source messages as graph-based structures can significantly improve communication efficiency and the accuracy of...
-
24
Modularity-Free Conflict-Averse Training for Generalized PINNs
Heejo Kong, Beomchul Park, Sung-Jin Kim, Seong-Whan Lee
cs.AI
Physics-informed neural networks (PINNs) have become a powerful framework for solving PDEs by embedding physical laws into differentiable objectives. Despite their advances, training PINNs remains fragile: recent conflict-averse optimization schemes alleviate gradient interference between residual and boundary losses, but we show that their effectiveness deteriorates as model capacity increases. In this paper, we identify a capacity-induced...
-
25
BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling
Bharathi Kannan Nithyanantham, Clemens Kujat, Tobias Sesterhenn, Stefan Telgmann, Jörn Plönnigs, Stefan Lüdtke,...
cs.AI
Large language models (LLMs) are increasingly applied to computer-aided design (CAD) to generate design artifacts from textual instructions. In engineering practice, this requires more than creating new geometry, models must also understand existing scenes, edit them correctly, and preserve semantics and relations. However, many CAD benchmarks focus on creating new models rather than editing existing ones, and mostly evaluate geometric...
-
26
RACL: Reasoning-Agent Control Layers for Continuous Metaheuristic Learning
Antón Asla Manzárraga
cs.AI · cs.MA
This paper introduces RACL, a Reasoning-Agent Control Layer for metaheuristics. RACL places a reasoning agent above an existing optimizer. The agent does not replace the optimizer and does not modify business constraints. Instead, it controls the optimizer's internal search behavior by observing operational memory, reasoning over past behavior, formulating bounded hypotheses, testing interventions, evaluating outcomes, applying guardrails,...
-
27
Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring
Po-Chin Chang, Nicholas Hogan, Aske Plaat, Michiel T. van der Meer
cs.AI · cs.CL · cs.HC · cs.LG
LLMs can personalize education, although current static-prompt tutoring systems struggle to adapt to diverse academic disciplines. We develop and test a system with subject-aware prompting, based on 14 pedagogical features (e.g., tutor scaffolding, student understanding) extracted from raw transcripts. We first train a prompt routing model in a simulation environment, and then deploy it for online adaptation with actual high-school students....
-
28
ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research
Zhibang Yang, Xinke Jiang, Yuzhen Xiao, Ruizhe Zhang, Yue Fang, XinFei Wan, Zhengxing Song, Yuxuan Liu, Yuheng...
cs.AI · cs.MA
Open-ended deep research (OEDR) requires systems to acquire knowledge through multi-round retrieval and generate coherent long-form reports. The outline plays a central role as a structural scaffold that coordinates retrieval, evidence organization, and generation. However, existing methods either fix the outline before writing or refine it with local heuristics, leading to scaffold drift under continuous information accumulation and delayed...
-
29
Multi-Head Attention-Based Feature Extractor Integration with Soft Actor-Critic for Porosity Prediction and Process Parameter Optimization in Additive Manufacturing
Kianoush Aqabakee, Leonardo Stella
cs.AI
Additive manufacturing process optimization requires precise parameter control to minimize defects such as porosity. Traditional reinforcement learning (RL) approaches using discrete action spaces suffer from slow convergence and susceptibility to local optima, limiting their effectiveness for high-precision manufacturing tasks. This study addresses these limitations by employing a continuous action space combined with a novel architecture...
-
30
Residual-Space Evolutionary Optimization via Flow-based Generative Models
Zhuo Cao, Lena Krieger, Fernanda Nader, Xuan Zhao, Hanno Scharr, Ira Assent
cs.AI
Data editing with generative methods typically requires differentiable objectives and gradient-based search. However, these assumptions break down in flow-based settings, where edits are performed through forward and backward integration and often involve non-differentiable or black-box objectives. We introduce residual-space evolutionary optimization, a model-agnostic framework that addresses this gap by combining flow-based generative...
-
31
Process-Verified Reinforcement Learning for Theorem Proving via Lean
Minsu Kim, Se-Young Yun
cs.AI
While reinforcement learning from verifiable rewards (RLVR) typically has relied on a single binary verification signal, symbolic proof assistants in formal reasoning offer rich, fine-grained structured feedback. This gap between structured processes and unstructured rewards highlights the importance of feedback that is both dense and sound. In this work, we demonstrate that the Lean proof assistant itself can serve as a symbolic process...
-
32
Autonomous Event-Driven Multi-Agent Orchestration for Enterprise AI at Scale
Harsh Rao Dhanyamraju, Leonidas Raghav, Aaron Lee
cs.AI
Enterprise AI aims to move toward continuous event monitoring, detection, and action across specialist agents, yet existing multi-agent systems largely assume discrete request-response workflows and remain underexplored at enterprise scale. We evaluate DAG Plan and Execute and ReAct across 208 production-derived enterprise scenarios spanning Persona (<10 agents), Department (20-80), and Enterprise (200) scales, and introduce a Task Manager...
-
33
Reward as An Agent for Embodied World Models
Pu Li, Zhigang Lin, Qiang Wu, Yongxuan Lv, Fei Wang, Shan You
cs.AI
While RL has become a promising tool for refining world models, existing methods largely rely on conservative rollouts near the training distribution, limiting exploration, behavioral diversity, and richer dynamic discovery. In this work, we challenge this conservative paradigm. We argue that the core limitation is not exploration itself, but the lack of reliable verification strategies to support broader exploration. Without reliable...
-
34
ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
Wenli Xiao, Jia Xie, Tonghe Zhang, Haotian Lin, Letian "Max" Fu, Haoru Xue, Jalen Lu, Yi Yang, Cunxi Dai, Zi Wang,...
cs.AI
Achieving dexterous robotic manipulation in the real world heavily relies on human supervision and algorithm engineering, which becomes a central bottleneck in the pursuit of general physical intelligence. Although emerging coding agents can generate code to automate algorithm search, their successes remain largely confined in digital environments. We conjecture that the missing abstraction to automate robotics research is a repeatable...
-
35
Advancing DialNav through Automatic Embodied Dialog Augmentation
Leekyeung Han, Sangwon Jung, Hyunji Min, Jinseong Jeong, Minyoung Kim, Paul Hongsuck Seo
cs.AI
For embodied agents capable of physical interaction, the capability to create and understand dialog is crucial to ensure both safety and effectiveness. While DialNav~\cite{han2025dialnav} provides a framework for holistic evaluation of the dialog--execution loop in photorealistic indoor navigation, its performance remains limited by a critical scarcity of training data (2K episodes). To address this, we propose an automatic generation...
-
36
PhysDrift: Bridging the Embodiment Gap in Humanoid Co-Speech Motion Generation
Zhangzhao Liang, Xiaofen Xing, Mingyue Yang, Wenlve Zhou, Xiangmin Xu
cs.AI
Humanoid robots require co-speech motions that are not only expressive and speech-aligned, but also physically executable under embodiment constraints. Existing co-speech generation pipelines are predominantly human-centric: motions are first generated in human-body representations such as SMPL-X and subsequently retargeted to humanoid robots. In this work, we identify a fundamental embodiment gap in this paradigm, where the mismatch between...
-
37
The Tao of Agency: Autotelic AI, Embedded Agency and Dissolution of the Self
Aritra Sarkar
cs.AI
Most artificial intelligence systems are built on the assumption that goals are exogenous and specified by the designer. Exploring what happens when an agent begins generating its own goals opens the field of autotelic AI. Agents are expected not merely to pursue objectives but to discover them. In this article, we trace its consequences through intrinsic motivation, resource-driven priors, causal-interventional learning, homeostasis, and...
-
38
eCNNTO: A Highly Generalizable ConvNet for Accelerating Topology Optimization
Shengbiao Lu, Xiaodong Wei
cs.AI
This work proposes an element-based Convolutional Neural Network (CNN) to accelerate density-based Topology Optimization (TO), termed eCNNTO. TO generally undergoes a large number of iterations, where finite element analysis is performed in every iteration, leading to the efficiency bottleneck especially when dense meshes are used to achieve high-resolution designs. To address this limitation, eCNNTO is proposed to build upon Kallioras et al....
-
39
Multi-Agent Transactive Memory
To Eun Kim, Xuhong He, Dishank Jain, Ambuj Agrawal, Negar Arabzadeh, Fernando Diaz
cs.AI · cs.CL · cs.IR
The decentralized deployment of LLM agents with diverse capabilities across diverse tasks motivates infrastructure for knowledge sharing across heterogeneous agent populations. Just as search engines index human-generated artifacts to support human problem solving, retrieval systems can organize agent-generated artifacts for reuse across agent populations. We extend retrieval-augmented generation - which demonstrates the value of...
-
40
MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments
Wei Yu, Suxing Liu, Minjie Yu, Jiahao Wang, Zhijian Zheng, Haocheng Deng, Bing Li
cs.AI
Deep research agents have demonstrated remarkable capabilities in autonomous information gathering and synthesis, yet their training remains constrained by the static nature of simulated environments, the limits of fact-retrieval-only task designs, and the inefficiency of outcome-based reinforcement learning. In this work, we propose MetaResearcher, a novel framework that scales deep research agent training across four synergistic dimensions....
-
41
A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models
Jiayi Wang, Xu-Yao Zhang
cs.AI
Although large language models (LLMs) have shown strong capabilities across a wide range of tasks, their outputs often remain unreliable and may contain hallucinations, making uncertainty estimation (UE) essential for building trustworthy LLMs. In practice, many mainstream LLMs are only accessible through restricted APIs, where internal signals such as logits and hidden states are unavailable, making black-box UE especially important....
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.