AI News Archive: July 6, 2026 — Part 10
Sourced from 500+ daily AI sources, scored by relevance.
- Who Responds When the Driver Is Gone? A Framework for Human Intent Understanding
As autonomous vehicles progress toward fully driverless mobility, a critical question emerges: who understands and responds to passengers when the human driver is absent? Existing autonomous driving systems primarily optimize predefined navigation and control objectives from external scene observati...
- Toward Personalized Social Robots for Child Well-being: Data Requirement Principles from a Recommender-System Perspective
Social robots are increasingly deployed in clinical settings to support the well-being of children, where effective support must be personalized to each child. Personalization, choosing the robot action best suited to each child, can be framed as a recommendation problem, and a recently proposed rec...
- PAGE: Towards Practical Human-level Gaze Target Estimation
Gaze target estimation, the task of predicting where a person is looking in a scene, is crucial to understanding human attention and intent. It is a challenging task that combines high-level understanding of global scene semantics and precise spatial reasoning using human appearance (e.g. pose, eye ...
- Strategic Buying Agents
Agentic AI is shifting online shopping from search toward delegated purchasing, where autonomous buying agents monitor markets and decide when to buy on a consumer's behalf. We study the design of such strategic buying agents, which must decide when to purchase within a finite shopping window, trans...
- Selective Disclosure Watermarking for Large Language Models
Watermarking methods embed imperceptible and verifiable signals into text generated by large language models (LLMs). Existing approaches include zero-bit schemes for distinguishing synthetic text from human writing and multi-bit schemes for embedding metadata. However, current multi-bit watermarking...
- Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning
Parameter-efficient fine-tuning still leaves a broad space of behavior-changing updates reachable, so a poisoned objective can be represented and optimized. We study an alternative: adaptation constrained to the subspace estimated from a trusted pool of existing task adapters. On flan-t5-large with ...
- Privacy-Preserving Robustness Verification for Neural Networks
Neural network verification and data privacy are inherently in tension: verification demands full access to model parameters and input data, yet both are increasingly restricted by privacy regulations and intellectual property constraints. This tension has left robustness verification impractical in...
- Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses
Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage information, and context. While this has improved the agent's functionality and continuity across tasks, it has also introduced a new attack surface: the agent...
- HilEnT: Hilbert, Entropy Transformed Image Based Malware Detection
With the increasing threat of malware across various software related domains, malware detection and classification is critical to determine the response actions. Different strategies have been adopted to address the challenge of malware detection. With the advent of deep learning techniques, malwar...
- RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities
LLM agents are increasingly applied to vulnerability analysis, but existing benchmarks have not kept pace. They typically rely on small non-compilable snippets, focus on binary classification (vulnerable or not), and do not account for the risk that publicly-released datasets are part of model train...
- Untrusted Content Masking for Web Agents with Security Guarantees
Defenses that provide security guarantees against prompt injection attacks rely on strict isolation between trusted instructions and untrusted data. In text-based environments such as tool-use APIs, this separation arises naturally: agents can reason from interface definitions without ever processin...
- When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents
Persistent personal agents combine long-term memory with access to users' external environments, enabling personalized foreground assistance and proactive background execution. This integration also creates a new path to compromise: untrusted external content can be silently written into persistent ...
- Agent Data Injection Attacks are Realistic Threats to AI Agents
AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security has primarily focused on indirect prompt injection (IPI). Its most well-studied category is instruction injection, where attacker-controlled untrusted d...
- From Multiplicity to Vulnerability: Privacy Amplification Risk from One-Dataset-Multiple-Model Exposure
To efficiently exploit a valuable data source (e.g., facial or medical images), it is frequently harnessed to fulfill multiple learning objectives (e.g., facial recognition, age estimation, and race classification). Each trained model is then deployed as an independent API service for corresponding ...
- Look-Ahead-Freedom as Temporal Non-Interference: A Verifiable Correctness Property for Backtesting and Agentic Trading Pipelines
Look-ahead bias (using information from after a decision epoch to make the decision at that epoch) is the dominant way a backtest or a machine-learning evaluation flatters a system that will disappoint in deployment. The field manages it with construct-specific recipes and empirical detectors, which...
- Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers
Fully homomorphic encryption (FHE) enables computation on encrypted data, but practical encrypted Transformer inference is bottlenecked by the sequential composition of many nonlinear blocks. We study whether Structured Newton Layer Parallelism (SNLP) can make this inter-layer composition more FHE-f...
- Towards Personalized Differentially Private Learning for Decentralized Local Graphs
Graph-structured data is increasingly generated and stored in decentralized environments, such as social platforms, mobile applications, and edge networks, where users maintain control over their local graph data. However, collecting and analyzing such decentralized graph data for downstream learnin...
- F-ACVAE: A Federated Adaptive Conditional Variational Auto-Encoder for Privacy-Preserving Intrusion Detection in IoT Networks
The rapid proliferation of Internet of things (IoT) devices has significantly expanded the cyber-attack surface, necessitating robust and privacy-preserving intrusion detection systems (IDS). However, centralized learning approaches often suffer from severe performance degradation due to high-dimens...
- Governed Caste Reassignment in Heterogeneous Swarms: An Asymmetric-Trust Protocol with Audited Operator Countersignature
In heterogeneous robot swarms, caste reassignment (rebinding a robot to a new capability-bound role) is a high-frequency runtime event driven by battery, payload, and priority changes. Existing approaches treat it as an internal allocation algorithm and do not expose the reassignment to external aut...
- Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority
Autonomous agents are moving from sandboxed text generators to operators of code, data, and physical infrastructure, and they increasingly learn while deployed. This reopens a question that alignment techniques answer only probabilistically: after an agent has adapted in the field, is the running sy...
- Is Three the Magic Number? An Empirical Evaluation of LLM-Based Repair Loops
Iterative repair loops have become a core design pattern in LLM-based software engineering systems. These workflows repeatedly generate, validate, and repair artifacts using feedback such as compiler errors or test failures. Despite their widespread use, the impact of repair-loop iteration limits re...
- Latent Programming Horizons in Coding Agents
A coding agent solving a software-engineering task spends dozens of steps reasoning, editing code, and running tests, yet little is known about what the underlying language model internally represents about the program it is working on. We show that the residual streams of language models under codi...
- On the risk of coding before testing: An empirical study on LLM-based test generation workflow
Large Language Models (LLMs) are increasingly used in software engineering workflows to generate both source code and test suites. This dual capability has enabled emerging development paradigms, including test-first and agentic workflows, where a single model is producing and validating implementat...
- From Failing to Passing: Evolving Natural Language Prompt Optimization Rules for LLM Code Generation
Large language models are known to be sensitive to prompt formulation. Even minor variations in wording can substantially degrade performance. This sensitivity reveals an opportunity: if prompt phrasing can harm performance, can it be used to improve it? To investigate this question, we introduce a ...
- LLM-Based Test Oracles: Source-of-Authority Taxonomy -- A Systematic Literature Review
Large language models (LLMs) are increasingly used to produce test oracles, the part of a test that decides whether observed behavior is correct. Yet a clear account of where these oracles draw their authority is missing. Prior secondary studies organize the area by oracle form or by LLM technique. ...
- A Comprehensive Study of Implementation Bugs in Multi-modal Agents
Multi-Modal Agents (M-agents), empowered by Large Language Models (LLMs), excel in various complex, open-world scenarios such as autonomous driving and robotics. However, their unique requirements to interact with dynamic and diverse multi-modal environments introduce novel implementation challenges...
- Real-World Perturbation Testing of Autonomous Driving Systems
Autonomous Driving Systems (ADS) must operate reliably under diverse conditions, yet representative data for rare or adverse scenarios is difficult to obtain. Perturbation-based testing is widely used to assess robustness, but most studies focus on offline datasets or simulation, leaving open questi...
- Teaching LLMs a Low-Resource Language: Enhancing Code Completion in Pharo
Large Language Models (LLMs) unlocked new possibilities in automated code writing, becoming the backbone of most code completion tools. While LLMs excel in mainstream languages, they often lack support for the so-called low-resource languages where training data is scarce. As a result, these languag...
- E-CoDrive: A Co-Simulation Framework for Testing Energy-Critical Driving Scenarios
Autonomous driving research has largely focused on safety while giving limited attention to non-functional aspects such as energy consumption and sustainability. As Autonomous Electric Vehicles (AEVs) become increasingly common in urban traffic, understanding how complex traffic dynamics influence t...
- Cam2Sim: Neural Scenario Reconstruction for Closed-Loop Autonomous Driving Simulation
Simulation-based testing enables safe and repeatable evaluation of autonomous driving systems, but its effectiveness is limited by the gap between synthetic simulator outputs and real-world camera observations. To address this problem, we present Cam2Sim, a tool that transforms real-world driving re...
- Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards
Automatic data visualization generation has advanced rapidly with multi-modal large language models, yet existing efforts largely focus on static charts and overlook the interactive dashboards commonly used for real-world data exploration. We introduce Dashboard2Code, a novel task that requires a mo...
- ToolFailBench: Diagnosing Tool-Use Failures in LLM Agents
Tool calling is central to modern language model agents, but aggregate benchmark scores often hide where tool use fails. A model that never calls a needed tool and a model that calls the tool but ignores the result can look similar under final task accuracy. We introduce ToolFailBench, a diagnostic ...
- Can LLMs Really Recover Microservice Failures? A Recovery-Aware Evaluation of Diagnosis-to-Action Reasoning
Large language models (LLMs) are increasingly used to interpret operational evidence and assist incident response in cloud-native microservice systems. However, recovery-oriented use cases require more than identifying a root cause. After observing symptoms and diagnosing a fault, an operator or age...
- Finetuning Lightweight LLMs for Control Flow Graph Generation
Control Flow Graph (CFG) is an important program representations for software analysis, code understanding, and software maintenance. Traditional CFG generation techniques mainly rely on bytecode or abstract syntax trees. However, these approaches usually require complete, compilable, and syntax err...
- LLM-Driven CI-CD Workflow Intelligence for Cyber Systems Engineering
CI/CD workflows have become executable operational policy: they decide what gets built, tested, released, and deployed, and they mediate how maintainers interact with delivery infrastructure. That makes them an important measurement point for cyber-systems engineering. Recent large language model (L...
- Three-Phase Evaluation of AI-Assisted Software Development Life Cycle
This paper presents an exploratory evaluation of how increasing levels of AI autonomy affect software development productivity, requirement adherence, and developer cognitive workload. A team of four developers reimplemented the same full-stack web application across three sequential phases: partial...
- When AI Is Wrong on Purpose: How Students Respond to Buggy GenAI Code
As Generative AI (GenAI) becomes increasingly central to software development, CS education is integrating prompt-centered workflows where students describe intended program behavior in natural language to elicit code. However, professional practice requires careful review and verification of GenAI-...
- Using Process Mining to Generate AI Agents from Software Engineering Process Records
Integrating AI agents into Software Engineering (SE) raises an important challenge: how can we specify and realize AI agents that work effectively alongside humans in hybrid SE teams? Determining the right granularity and separation of concerns for such agents is non-trivial. Coarse-grained agents m...
- A Temporal Reasoning Benchmarking Framework for LRMs via Difficulty-controlled and Dynamic Test Generation
Defining the reasoning boundaries and ensuring the reliability of Large Reasoning Models (LRMs) remains a critical challenge. Current benchmarks primarily rely on static datasets susceptible to data contamination or synthetic tasks lacking fine-grained difficulty control. Furthermore, standard outco...
- AI Agent Pull Requests on GitHub: Frequency, Structure, and Merge Conflict Rates
AI coding agents can create and submit pull requests (PRs) to a common repository at the same time; however, there is little research on the frequency of such concurrent submissions or the cost associated with them. In this study, we use the AIDev-pop dataset (33,596 PRs across 2,807 repositories) t...
- Correctness, confidence, and context: Framing software assurance in the AI age
Software engineering has a complicated relationship with "correctness". We recognize the challenges of full formal rigor as well as many required properties beyond functional correctness. Although we satisfice in practice, we are still stuck in the mindset that we could reason our way to correctness...
- Unified Audio Intelligence Without Regressing on Text Intelligence
Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A3B, a strong text-only MoE LLM. Audex adopts a simple unified design with a sing...
- SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
Streaming speech-to-speech language models aim to answer spoken queries directly with synthetic speech. However, standard speech and text benchmarks do not capture whether these systems behave naturally in conversations, where timing, turn-taking, prosody, interpersonal stance, language and dialect ...
- ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions
Speaker embeddings, or x-vectors, are widely used to represent speaker identity and speaker-related attributes, but existing embedding extractors are typically descriptive rather than generative: they map an observed speech segment to an x-vector, which is then used for downstream applications. We i...
- Towards Language-Agnostic Speech Inversion
Characteristic timing patterns are reflected in the acoustic speech signal, encompassing both vocal tract configuration and acoustic excitation. Previous studies have demonstrated that speech inversion (SI) systems can recover these timing patterns from speech, including oral tract variables (tongue...
- DuplexChat: Constructing Speaker-Separated Full-Duplex Dialogue Speech at Scale for Spoken Dialogue Language Modeling
Full-duplex spoken dialogue models are trained on conversational speech in which each speaker is represented as a separate stream, but existing large-scale public speech corpora are mostly monaural, making them unsuited for SDLM training. We present DuplexChat, an open-source corpus for full-duplex ...
- Ranking the Impact of Contextual Specialization in Neural Speech Enhancement
We systematically investigate neural speech enhancement systems, ranging from very small ($\sim$10\,k parameters) to medium-large ($\sim$2-5\,M parameters), which specialize to acoustic conditions using contextual information such as speaker identity, noise type, speaker gender, spoken language, and...
- Curated retrieval versus open web search in public AI information services: a coverage-trust trade-off
Public institutions increasingly use large language models (LLMs) to answer citizens' questions, often pairing a curated knowledge base with live web search, yet whether the sources behind these answers can be trusted has received little empirical scrutiny. We report a pre-launch expert evaluation o...
- Progressive Disclosure for LLM-Maintained Wiki Knowledge Bases: a Preregistered Ablation
LLM agents increasingly answer questions against knowledge bases they help maintain. A common intuition holds that progressive disclosure, a compact catalog plus a one-line summary per page so the agent loads only what it needs, should make this cheaper than consulting a large monolithic index. We t...
- CanniUplift: A Holistic Framework for Mitigating Seller and Incentive Cannibalization in E-commerce Uplift Modeling
Personalized incentive allocation is vital for e-commerce, where uplift modeling is the standard for estimating Individual Treatment Effects (ITE). However, traditional models often fail in complex multi-seller environments with violations of the Stable Unit Treatment Value Assumption (SUTVA). We id...