2026年7月1日 技术热点总结

项目简介：Build digital human beings — autonomous, collaborative, and socially intelligent agents.

技术栈：Python、ai、ai-agents

核心介绍：behavior in populations of cognitive agents. Built on research from Fundamental Research Labs · @Fundamental Ava runs large populations of autonomous agents — each with its own memory, belief system, and social model — inside a shared environment and asks a simple question: what happens at the population level that nobody programmed in directly?** Individual agents are deliberately simple: a perceive-deliberate-act loop,

项目数据：⭐ 592 Stars，🍴 57 Forks

项目简介：Premium hand-drawn animated architecture diagram Codex skill

技术栈：Python

核心介绍：JSON spec -> .excalidraw + .png + animated .gif Gallery · Quick Start · Features · Spec · Verification lanshu-animated-architecture-diagram is a Codex skill and local renderer for creating premium black-canvas technical diagrams with hand-drawn typography, editable Excalidraw output, static PNG previews, and genuinely animated GIFs. It is designed for article explanations, system architecture diagrams, process diagrams, and DailyDoseOfDS-style black-background technical sketches.

关键特性：Genera…

While text-guided image editing has made remarkable progress, it remains limited in structural portrait retouching. Textual descriptions struggle to convey fine-grained changes to facial features and body proportions. To address this gap, we introduce Exemplar-Based Portrait Photo Retouching, where the model is given an exemplar pair and tasked with inferring and applying the same retouching operations to a new query image. Existing exemplar-based editing methods primarily focus on tasks with pronounced visual transformations. In contrast, structural portrait retouching involves extremely d…

Multi-agent large language model (LLM) systems often rely on verifier and critic agents to suppress hallucinations, but verification is delayed. During this delay, false claims can propagate through the agent network. We model this process as delayed consensus on a graph with grounded corrector nodes. Spectral decomposition by the grounded Laplacian yields a closed-form stability threshold for the verification dose: correction that is too strong or too delayed can turn consensus into oscillation. The most unstable regime occurs when the communication and verification delays coincide; for de…

Vision-Language-Action (VLA) models enable instruction-driven robotic manipulation, but they inherit oversized language backbones from pretrained VLMs whose capacity far exceeds what is needed for short robotic instructions. This raises a basic question: how much of a VLA model is actually necessary for closed-loop control? In this work, we study architectural redundancy in VLA models by using transformer block removal as a controlled intervention. We introduce Drop-Then-Recovery (DTR), an analysis protocol that removes selected blocks from a pretrained VLA model and then fine-tunes the res…

Recent work has demonstrated the potential of large language models (LLMs) for program optimization, a key challenge in programming languages. We propose a blackbox adaptation method called Retrieval Augmented Search (RAS) that performs beam search over candidate optimizations; at each step, it retrieves in-context examples from a given training dataset of slow-fast program pairs to guide the LLM. Critically, we find that performing contextual retrieval based on an LLM-generated natural language description significantly outperforms retrieval based on the source code. We also propose AEGIS,…

Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an external vision encoder. However, existing methods typically align a fixed layer of the language backbone, overlooking the fine-grained structure of Transformer models. In this work, we propose Head-Wise Representation Alignment (HeRA), a method that enforces cross-modal alignment at the level of individual attention heads. Our approach is grounded in the Platonic Representation Hypothesis, focusing on preserving …

Most coding-agent benchmarks are static: an agent receives a complete task description up front and is judged only by its final code. Real coding assistance is interactive, with users clarifying goals, adding constraints, and correcting mistakes over multiple turns. We introduce SWE-Together, a multi-turn benchmark reconstructed from real user-agent coding sessions. To make real interactions verifiable, we curate 109 repository-level tasks from 11,260 recorded sessions, selecting sessions with recoverable repository states, clear user goals, and observable outcomes. To replay these interact…