arXiv:2605.14290v1 Announce Type: cross Abstract: ReAct has become the default architecture across LLM agents, and many existing web agents follow this paradigm. We argue that it is the wrong default for web agents. Instead, web agents should default to plan-then-execute: commit to a task-specific program before observing runtime web content, then execute it. The reason […]
Data-Augmented Game Starts for Accelerating Self-Play Exploration in Imperfect Information Games
arXiv:2605.14379v1 Announce Type: cross Abstract: Finding approximate equilibria for large-scale imperfect-information competitive games such as StarCraft, Dota, and CounterStrike remains computationally infeasible due to sparse rewards and challenging exploration over long horizons. In this paper, we propose a multi-agent starting-state sampling strategy designed to substantially accelerate online exploration in regularized policy-gradient game methods for two-player […]
HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts
arXiv:2605.13997v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) layers route tokens through a handful of experts, and learning-free compression of these layers reduces inference cost without retraining. A subtle obstruction blocks every existing compressor in this family: three experts can each be pairwise compatible yet form an irreducible cycle when merged together, so any score […]
Why Retrieval-Augmented Generation Fails: A Graph Perspective
arXiv:2605.14192v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become a powerful and widely used approach for improving large language models by grounding generation in retrieved evidence. However, RAG systems still produce incorrect answers in many cases. Why RAG fails despite having access to external information remains poorly understood. We present a model-internal study of […]
ARES-LSHADE: Autoresearch-Enhanced LSHADE with Memetic Polish for the GNBG Benchmark
arXiv:2605.13877v1 Announce Type: cross Abstract: We present ARES-LSHADE, a memetic differential-evolution variant submitted to the GECCO 2026 competition on LLM-designed evolutionary algorithms for the Generalized Numerical Benchmark Generator (GNBG). The algorithm builds on the LLM-LSHADE 2025 winner, contributing two new components: (a) a scout-augmented mutation operator with adaptive CMA-ES integration, produced by an autonomous research […]
Towards the Next Frontier of LLMs, Training on Private Data: A Cross-Domain Benchmark for Federated Fine-Tuning
arXiv:2605.13936v1 Announce Type: cross Abstract: The recent success of large language models (LLMs) has been largely driven by vast public datasets. However, the next frontier for LLM development lies beyond public data. Much of the world’s most valuable information is private, especially in highly regulated sectors such as healthcare and finance, where data include patient […]
CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
arXiv:2605.14084v1 Announce Type: cross Abstract: Code agents must both reason over long-horizon repository state and obey strict tool-use protocols. In paired Instruct/Thinking checkpoints, these capabilities are complementary but misaligned. The Instruct model is concise and tool-disciplined, whereas the Thinking model offers stronger planning and recovery behavior but often over-deliberates and degrades agent performance. We present […]
Artificial Intelligence-Assistant Cardiotocography: Unified Model for Signal Reconstruction, Fetal Heart Rate Analysis, and Variability Assessment
arXiv:2605.14242v1 Announce Type: cross Abstract: The monitoring of fetal heart rate (FHR) and the assessment of its variability are crucial for preventing fetal compromise and adverse outcomes. However, traditional methods encounter limitations arising from equipment performance, data transmission, and subjective assessments by doctors. We have developed a tailored AI-based FHrCTG model specifically for FHR monitoring, […]
A Two-Dimensional Framework for AI Agent Design Patterns: Cognitive Function and Execution Topology
arXiv:2605.13850v1 Announce Type: new Abstract: Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus on execution topology — how data flows — while cognitive science surveys focus on cognitive function — what the agent does. Neither axis alone disambiguates architecturally distinct systems: the same Orchestrator-Workers topology […]
Analog RF Computing: A New Paradigm for Energy-Efficient Edge AI Over MU-MIMO Systems
arXiv:2605.14331v1 Announce Type: cross Abstract: Modern edge devices increasingly rely on neural networks for intelligent applications. However, conventional digital computing-based edge inference requires substantial memory and energy consumption. In analog radio frequency (RF) computing, a base station (BS) encodes the weights of the neural networks and broadcasts the RF waveforms to the clients. Each client […]
FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery
arXiv:2605.14854v1 Announce Type: cross Abstract: Human Mesh Recovery (HMR) is fundamentally ambiguous: under occlusion or weak depth cues, multiple 3D bodies can explain the same image evidence. This ambiguity is not uniform across the body, as torso pose and root structure are often relatively well constrained, whereas distal articulations such as the arms and legs […]
Collaborative Yet Personalized Policy Training: Single-Timescale Federated Actor-Critic
arXiv:2605.14423v1 Announce Type: cross Abstract: Despite the popularity of the actor-critic method and the practical needs of collaborative policy training, existing works typically either overlook environmental heterogeneity or give up personalization altogether by training a single shared policy across all agents. We consider a federated actor-critic framework in which agents share a common linear subspace […]