SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering

Classés selon la proximité de leur titre et de leur résumé avec ceux de cet article. Sélectionnez-en pour les lire ensemble.

Les articles les plus proches

1. Très proche Pas pertinent

   Synergy: A Next-Generation General-Purpose Agent for Open Agentic Web

   Xiao-Hang Nie, Zi-Han Guo, Ke Yang et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 1 fois · Pas encore résumé

   Résumé scientifique

   AI agents are rapidly expanding in both capability and population: they now write code, operate computers across platforms, manage cloud infrastructure, and make purchasing decisions, while open-source frameworks such as OpenClaw are putting personal agents in the hands of millions and embodied agents are spreading across smartphones, vehicles, and robots. As the internet prepares to host billions of such entities, it is shifting toward what we call Open Agentic Web, a decentralized digital ecosystem in which agents from different users, organizations, and runtimes can discover one another, negotiate task boundaries, and delegate work across open technical and social surfaces at scale. Yet m…

2. Proche Pas pertinent

   ClawGym: A Scalable Framework for Building Effective Claw Agents

   Fei Bai, Huatong Song, Shuang Sun et al. · 2026 · Computation and Language · preprint, non relu par les pairs · cité 15 fois · Résumé IA disponible

   Résumé scientifique

   Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains constrained by the absence of a systematic framework, especially one for synthesizing verifiable training data and integrating it with agent training and diagnostic evaluation. To address this challenge, we present ClawGym, a scalable framework that supports the full lifecycle of Claw-style personal agent development. Concretely, we construct ClawGym-SynData, a diverse dataset of 13.5K filtered tasks synthesized from persona-driven intents and skill-grounded operations, paired with realistic mock workspaces and hybrid v…

3. Proche Pas pertinent

   Code as Agent Harness

   Xuying Ning, Katherine Tieu, Dongqi Fu et al. · 2026 · Computation and Language · preprint, non relu par les pairs · cité 54 fois · Résumé IA disponible

   Résumé scientifique

   Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification. We frame this shift through the lens of agent harnesses and introduce code as agent harness: a unified view that centers code as the basis for agent infrastructure. To systematically study this perspective, we organize the survey around three connected layers. First, we study the harness interface, where code c…

4. Proche Pas pertinent

   Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems

   Jia-Cheng Liu, Xiao-Han Zhao, Xin-Yi Shang et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 56 fois · Pas encore résumé

   Résumé scientifique

   Claude Code is an agentic coding tool that can run shell commands, edit files, and call external services on behalf of the user. This study describes its architecture by analyzing the publicly available source code and comparing it with two independent open-source AI agent systems, OpenClaw and Hermes Agent, that answer many of similar or even the same design questions. Our analysis identifies five human values, philosophies, and needs that motivate the architecture: human decision authority, safety, security, and privacy, reliable execution, capability amplification, and contextual adaptability. We then trace them through thirteen design principles to implementation choices. The core of the…

5. Proche Pas pertinent

   Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses

   Jiahang Lin, Shichun Liu, Chengjun Pan et al. · 2026 · Computation and Language · preprint, non relu par les pairs · cité 166 fois · Résumé IA disponible

   Résumé scientifique

   Harnesses are now central to coding-agent performance, mediating how models interact with tools and execution environments. Yet harness engineering remains a manual craft, because automating it faces a heterogeneous action space across editable components, voluminous trajectories that bury actionable signal, and edits whose effect is hard to attribute. We introduce Agentic Harness Engineering (AHE), a closed loop that addresses these challenges through three matched observability pillars: (1) component observability gives every editable harness component a file-level representation so the action space is explicit and revertible; (2) experience observability distills millions of raw trajector…

6. Proche Pas pertinent

   Human Tool: An MCP-Style Framework for Human-Agent Collaboration

   Yuan-Rong Tang, Hui-Ling Peng, Bing Zhao et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 2 fois · Pas encore résumé

   Résumé scientifique

   Human-AI collaboration faces growing challenges as AI systems increasingly outperform humans on complex tasks, while humans remain responsible for orchestration, validation, and decision oversight. To address this imbalance, we introduce Human Tool, an MCP-style interface abstraction, building on recent Model Context Protocol designs, that exposes humans as callable tools within AI-led, proactive workflows. Here,"tool"denotes a coordination abstraction, not a reduction of human authority or responsibility. Building on LLM-based agent architectures, we operationalize Human Tool by modeling human contributions through structured tool schemas of capabilities, information, and authority. These s…

7. Proche Pas pertinent

   Software as Content: Dynamic Applications as the Human-Agent Interaction Layer

   Mulong Xie, Yang Xie · 2026 · Human-Computer Interaction · preprint, non relu par les pairs · cité 2 fois · Pas encore résumé

   Résumé scientifique

   Chat-based natural language interfaces have emerged as the dominant paradigm for human-agent interaction, yet they fundamentally constrain engagement with structured information and complex tasks. We identify three inherent limitations: the mismatch between structured data and linear text, the high entropy of unconstrained natural language input, and the lack of persistent, evolving interaction state. We introduce Software as Content (SaC), a paradigm in which dynamically generated agentic applications serve as the primary medium of human-agent interaction. Rather than communicating through sequential text exchange, this medium renders task-specific interfaces that present structured informa…

8. Proche Pas pertinent

   Context Engineering: From Prompts to Corporate Multi-Agent Architecture

   Vera V. Vishnyakova · 2026 · arXiv.org · preprint, non relu par les pairs · cité 2 fois · Pas encore résumé

   Résumé scientifique

   As artificial intelligence (AI) systems evolve from stateless chatbots to autonomous multi-step agents, prompt engineering (PE), the discipline of crafting individual queries, proves necessary but insufficient. This paper introduces context engineering (CE) as a standalone discipline concerned with designing, structuring, and managing the entire informational environment in which an AI agent makes decisions. Drawing on vendor architectures (Google ADK, Anthropic, LangChain), current academic work (ACE framework, Google DeepMind's intelligent delegation), enterprise research (Deloitte, 2026; KPMG, 2026), and the author's experience building a multi-agent system, the paper proposes five contex…

Les travaux antérieurs sur lesquels il s’appuie

1. Apparenté Pas pertinent

   AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

   Qing-Yun Wu, Gagan Bansal, Jieyu Zhang et al. · 2023 · cité 3 070 fois · Résumé IA disponible

   Résumé scientifique

   AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ combinations of LLMs, human inputs, and tools. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic infrastructure to build diverse applications of various complexities and LLM capacities. Empirical studies demonstrate the effectiveness of the framework in many example ap…

2. Apparenté Pas pertinent

   Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

   Patrick Lewis, Ethan Perez, Aleksandra Piktus et al. · 2020 · Neural Information Processing Systems · cité 20 370 fois · Résumé IA disponible

   Résumé scientifique

   Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, their ability to access and precisely manipulate knowledge is still limited, and hence on knowledge-intensive tasks, their performance lags behind task-specific architectures. Additionally, providing provenance for their decisions and updating their world knowledge remain open research problems. Pre-trained models with a differentiable access mechanism to explicit non-parametric memory can overcome this issue, but have so far been only investigated for extractive downstream tasks. We explore a general-purpose …

3. Apparenté Pas pertinent

   Lost in the Middle: How Language Models Use Long Contexts

   Nelson F. Liu, Kevin Lin, John Hewitt et al. · 2023 · Transactions of the Association for Computational Linguistics · cité 5 776 fois · Résumé IA disponible

   Résumé scientifique

   While recent language models have the ability to take long contexts as input, relatively little is known about how well they use longer context. We analyze the performance of language models on two tasks that require identifying relevant information in their input contexts: multi-document question answering and key-value retrieval. We find that performance can degrade significantly when changing the position of relevant information, indicating that current language models do not robustly make use of information in long input contexts. In particular, we observe that performance is often highest when relevant information occurs at the beginning or end of the input context, and significantly de…

Les articles qui le citent

1. Proche Pas pertinent

   Self-Harness: Harnesses That Improve Themselves

   Hangfan Zhang, Shao Zhang, Kangcong Li et al. · 2026 · Computation and Language · preprint, non relu par les pairs · cité 123 fois · Résumé IA disponible

   Résumé scientifique

   The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment. Because different models exhibit distinct behaviors, effective harness design is inherently model-specific. Yet agent harnesses are still largely engineered by human experts, a paradigm that scales poorly as modern LLMs become increasingly diverse and rapidly evolving. In this paper, we introduce Self-Harness, a new paradigm in which an LLM-based agent improves its own operating harness, without relying on human engineers or stronger external agents. We operationalize Self-Harness as an iterative loop with three stages: Weakness Mining, which ident…

2. Proche Pas pertinent

   Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

   Ru-Han Wang, Yu-Cheng Shi, Zong-Xia Li et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 15 fois · Pas encore résumé

   Résumé scientifique

   The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools, and coordinates execution. As models, APIs, environments, and requirements evolve, the harness must be continually modified. Before such a change can be made, a developer or coding agent must identify all code locations that implement the target behavior. This is difficult because production harnesses are large, tightly coupled, and behaviorally distributed, while modification requests describe what the system should do and repositories are organized by files and modules. Code search, repository indexing, and long-context processing eas…

3. Apparenté Pas pertinent

   Code Is the Body: Agent-Owned Software Bodies for Recursive Evolution and Descent

   Roy Zhao, Zhen-Yu Zhao · 2026 · arXiv.org · preprint, non relu par les pairs · cité 3 fois · Pas encore résumé

   Résumé scientifique

   Personalized AI agents are often configurable without giving users control over the artifacts that determine their future behavior. We present OurArk, an architecture for persistent personal agents centered on an agent-owned software body: an identity-bearing, inspectable, and versioned artifact under human custody. The body contains behavior-defining code, prompts, tools, skills, policies, tests, and evolution mechanisms. Memories and credentials remain private instance state, while model inference is treated as a replaceable external service. OurArk defines governed self-evolution and recursive descent over the same body. Self-evolution produces isolated candidate changes that are validate…

4. Apparenté Pas pertinent

   ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation

   Qi-Hong Chen, Aaron Imani, Iftekhar Ahmed · 2026 · arXiv.org · preprint, non relu par les pairs · cité 1 fois · Pas encore résumé

   Résumé scientifique

   Repository-level code generation requires implementing target functions while accounting for complex cross-file dependencies and project-specific conventions. Existing retrieval methods predominantly rely on lexical, structural, or semantic similarity, often overlooking repository functions that implement similar procedural logic despite differing in identifiers or application domains. We propose ProjAgent, a repository-level code generation system that introduces procedural similarity as an explicit retrieval signal. ProjAgent decomposes the target function into intermediate reasoning steps and employs an agentic workflow to retrieve repository functions that exhibit similar procedural beha…