arXiv AI
Jul 20
When Do Multi-Agent Systems Help? An Information Bottleneck Perspective
arXiv:2607. 16133v1 Announce Type: cross Abstract: LLM powered multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks.
AI agents
Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv AI
Jul 20
The AI Fiction Paradox
arXiv:2603. 13545v2 Announce Type: replace Abstract: AI development has a fiction dependency problem.
arXiv AI
Jul 20
Map as a Prompt: Learning Multi-Modal Spatial-Signal Foundation Models for Cross-scenario Wireless Localization
arXiv:2607. 15713v1 Announce Type: cross Abstract: Accurate and robust wireless localization is a critical enabler for emerging 5G/6G applications, including autonomous driving, extended reality, and smart manufacturing.
arXiv AI
Jul 20
NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs
arXiv:2607. 14186v2 Announce Type: replace-cross Abstract: Synthesizing training data to scale agent capabilities in LLM post-training is bottlenecked by substrate-bound task synthesis: tasks are generated from fixed tools, repositories, or skill graphs, so expanding coverage requires manual substrate engineering, transferring to a new domain demands bespoke infrastructure, and the resulting distributions inherit substrate biases rather than reflecting real-world demand.
arXiv AI
Jul 20
SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery
arXiv:2607. 16038v1 Announce Type: new Abstract: Scientific work increasingly spans heterogeneous artifacts -- papers, code, datasets, scientific file formats, model outputs, figures, manuscripts, and team decisions -- yet general-purpose AI assistants rarely preserve these objects as a coherent, auditable research state.
arXiv AI
Jul 20
Recursive Harness Self-Improvement
arXiv:2607. 15524v1 Announce Type: cross Abstract: Under model--harness co-evolution, harnesses are not merely inference-time scaffolds but data-generating components whose execution traces can shape future foundation models.
arXiv AI
Jul 20
Process Reward Informed Tree Rollout for Effective Multi-Turn RL
arXiv:2607. 15610v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories for advantage estimation.
arXiv AI
Jul 20
Think at 5 Hz, Act at 20 Hz: Asynchronous Fast-Slow Vision-Language-Action Inference for Closed-Loop Driving
arXiv:2607. 15621v1 Announce Type: cross Abstract: Large language models bring instruction following and scene reasoning to end-to-end driving, but their inference latency collides with the control rate a vehicle requires.
arXiv AI
Jul 20
Interaction-Aware Whole-Body Control for Compliant Object Transport
arXiv:2603. 03751v2 Announce Type: replace-cross Abstract: Cooperative object transport in unstructured environments remains challenging for assistive humanoids because strong, time-varying interaction forces can make tracking-centric whole-body control unreliable, especially in close-contact support tasks.
arXiv AI
Jul 20
Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios
arXiv:2604. 06742v2 Announce Type: replace-cross Abstract: The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift towards intent-driven software development, where autonomous agents are expected to design and deliver complete, runnable software systems from scratch.
arXiv AI
Jul 20
Frontier AI performance across the business disciplines: a case-grounded benchmark of knowledge work and analytical reasoning
arXiv:2607. 16057v1 Announce Type: cross Abstract: Large language models (LLMs) are improving rapidly as reflected in benchmark scores, yet these AI benchmarks largely test capabilities such as factual recall, narrow question answering, mathematical problem-solving, and coding and agentic tool-use.
arXiv Machine Learning
Jul 20
Learning Reach-Avoid Task with Reinforcement Learning: Vectorized Simulation and Benchmark
arXiv:2607. 15935v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) has a longstanding tradition in addressing the reach-avoid task problem, especially for controlling robotic arms.
arXiv Machine Learning
Jul 20
SpeechGuard: Online Defense against Backdoor Attacks on Speech Recognition Models
arXiv:2607. 15697v1 Announce Type: cross Abstract: Backdoor attacks pose a critical threat to neural network models, allowing attackers to implant a backdoor during the training phase by manipulating a small portion of the training data.
arXiv AI
Jul 20
Empathy as Predictive Misalignment Tolerance: A Co-Regulation Framework and the Regime Structure of Dialogue Repair
arXiv:2607. 15282v1 Announce Type: cross Abstract: Empathy is most often theorized as resonance: a mirroring of another's present emotional or cognitive state.
arXiv AI
Jul 20
DSWorld: A Data Science World Model for Efficient Autonomous Agents
arXiv:2607. 15901v1 Announce Type: new Abstract: Despite strong capabilities in data understanding and decision-making, autonomous data science agents still heavily rely on trial-and-error workflows that involve expensive computation.
arXiv AI
Jul 20
Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?
arXiv:2607. 15439v1 Announce Type: new Abstract: Our previous ARC-AGI-3 agent bundled executable world modeling, scheduled simplification, and exact replay verification, leaving unclear which idea accounted for its performance.
arXiv Machine Learning
Jul 20
Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents
arXiv:2607. 15657v1 Announce Type: cross Abstract: Multimodal AI agents increasingly rely on persistent long-term memory to ground generation in past visual and textual episodes.
arXiv Machine Learning
Jul 20
Time-varying Mixing Matrix Design for Energy-efficient Decentralized Federated Learning
arXiv:2512. 24069v2 Announce Type: replace Abstract: We consider the design of mixing matrices to minimize the operation cost for decentralized federated learning (DFL) in wireless networks, with focus on minimizing the maximum per-node energy consumption.
arXiv AI
Jul 20
GraphDx: A Cost-Aware Knowledge-Enhanced Multi-Agent Framework for Sequential Diagnosis
arXiv:2607. 15280v1 Announce Type: new Abstract: Sequential diagnosis requires balancing diagnostic accuracy against resource costs through iterative information gathering.
arXiv AI
Jul 20
LLM-Powered Agentic AI for 5G/6G Networks: A Tutorial and Survey on Architectures, Protocols, and Standardization
arXiv:2607. 16066v1 Announce Type: cross Abstract: Agentic Artificial Intelligence (AI), enabled by Large Language Models, marks a shift from rule-based automation toward autonomous, goal-driven control of Next-Generation Networks (NGNs).