arXiv AI
Jun 9
Repair Before Veto, When Repair Is Hidden: Quantum-Accessible Features for Repair-Augmented Constraint Learning
arXiv:2606. 08020v1 Announce Type: cross Abstract: Hard-constraint decision systems usually veto infeasible candidates.
AI agents
Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv AI
Jun 9
VisualLeakBench: Reproducible Action-Boundary Propagation Failures in Vision-Language Agents
arXiv:2606. 07595v1 Announce Type: cross Abstract: Vision-language agents increasingly consume screenshots, documents, and user interfaces before writing to memory, sending messages, or invoking external tools.
arXiv AI
Jun 9
Traxia: A Framework for Verifiable, Agent-Native Scientific Publishing
arXiv:2606. 08256v1 Announce Type: new Abstract: Verifiability, attribution, and reproducibility are foundational requirements of scientific knowledge, yet current publishing infrastructure does not enforce them at scale.
arXiv Machine Learning
Jun 9
Federated Large Language Models: Current Progress and Future Directions
arXiv:2409. 15723v3 Announce Type: replace Abstract: Large Language Models have achieved impressive performance across diverse applications, yet their training typically depends on centralized data collection, raising serious privacy and governance concerns.
arXiv AI
Jun 9
EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale
arXiv:2604. 17406v3 Announce Type: replace Abstract: The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science.
arXiv AI
Jun 9
VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation
arXiv:2606. 07992v1 Announce Type: new Abstract: As the Model Context Protocol (MCP) standardizes tool-calling for autonomous agents, it introduces a critical, unexamined attack surface: the error-handling loop.
arXiv AI
Jun 9
Online Agent-as-a-Judge: Situation-Generating Evaluation for Interactive Agents
arXiv:2606. 08200v1 Announce Type: new Abstract: Evaluating LLM-powered interactive social agents is challenging because socially relevant behaviors depend not only on isolated outputs, but also on prior interactions, social roles, and downstream actions.
arXiv AI
Jun 9
Efficient Skill Grounding via Code Refactoring with Small Language Models
arXiv:2606. 07999v1 Announce Type: new Abstract: Effective skill grounding is essential for deploying reusable skills in embodied agents, as even minor embodiment or environmental differences can render an entire skill incompatible.
arXiv AI
Jun 9
MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering
arXiv:2601. 22859v3 Announce Type: replace-cross Abstract: The evolution of Large Language Model (LLM) agents for software engineering (SWE) is constrained by the scarcity of verifiable datasets, a bottleneck stemming from the complexity of constructing executable environments across diverse languages.
arXiv AI
Jun 9
Meeting SLOs, Slashing Hours: Automated Enterprise LLM Optimization with OptiKIT
arXiv:2601. 20408v2 Announce Type: replace-cross Abstract: Enterprise LLM deployment faces a critical scalability challenge: organizations must optimize models systematically to scale AI initiatives within constrained compute budgets, yet the specialized expertise required for manual optimization remains a niche and scarce skillset.
arXiv AI
Jun 9
ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning
arXiv:2505. 21457v2 Announce Type: replace-cross Abstract: Active vision, also known as active perception, refers to actively selecting where and how to look in order to gather task-relevant information.
arXiv Machine Learning
Jun 9
AI-Native Closed-Loop Security for 6G-Enabled Cyber-Physical Systems: From Edge Detection to Network-Wide Mitigation
arXiv:2606. 08173v1 Announce Type: cross Abstract: In sixth-generation (6G) networks, billions of cyber-physical systems (CPSs) - autonomous vehicles, smart grids, industrial robots, and remote-surgical equipment - will run over ultra-reliable low-latency slices, collapsing the gap between a remote breach and physical harm to milliseconds, a budget perimeter firewalls and centralised security operations centres cannot meet.
arXiv Machine Learning
Jun 9
Code Is More Than Text: Uncertainty Estimation for Code Generation
arXiv:2606. 09577v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as code generators, where silently wrong programs pose real safety and reliability risks.
arXiv AI
Jun 9
TianJi-Environ: An Autonomous AI Scientist for Atmospheric Environmental Research
arXiv:2606. 07697v1 Announce Type: cross Abstract: As atmospheric environmental prediction continues to improve, interpretable validation of pollution mechanisms and feedback processes has become a main challenge in atmospheric chemistry.
arXiv AI
Jun 9
Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulation
arXiv:2606. 09236v1 Announce Type: cross Abstract: Autonomous Racing has seen remarkable progress through deep Reinforcement Learning (RL), primarily for four-wheeled vehicles.
arXiv AI
Jun 9
HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions
arXiv:2503. 14229v4 Announce Type: replace Abstract: Vision-and-Language Navigation (VLN) has been studied mainly in either discrete or continuous spaces, with little attention to dynamic, crowded environments.
arXiv AI
Jun 9
Harness Engineering for Physical AI: Robot Middleware Is the Harness Layer
arXiv:2606. 09416v1 Announce Type: cross Abstract: Robot middleware faces a new role in the era of Physical AI.
arXiv AI
Jun 9
DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking
arXiv:2602. 00238v2 Announce Type: replace-cross Abstract: Existing retrieval-augmented generation (RAG) systems often assume that each query has a single correct answer.
arXiv AI
Jun 9
Context Rot in AI-Assisted Software Development: Repurposing Documentation Consistency for AI Configuration Artifacts
arXiv:2606. 09090v1 Announce Type: cross Abstract: Developers increasingly provide AI coding assistants with persistent context through configuration files such as CLAUDE.
arXiv AI
Jun 9
FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks
arXiv:2505. 19662v4 Announce Type: replace Abstract: This paper introduces FieldWorkArena, a benchmark for agentic AI targeting real-world field work.