ClawGym: A Scalable Framework for Building Effective Claw Agents

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 Cité par cet article Pas pertinent

   Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents

   Bo-Wen Ye, Rang Li, Qi-Bin Yang et al. · 2026 · cité 67 fois · Pas encore résumé

   Résumé scientifique

   Large language models are increasingly deployed as autonomous agents for multi-step workflows in real-world software environments. However, existing agent benchmarks are limited by trajectory-opaque grading, underspecified safety and robustness evaluation, and narrow coverage of modalities and interaction paradigms. We introduce Claw-Eval, an end-to-end evaluation suite addressing these gaps with 300 human-verified tasks spanning 9 categories across three groups: general service orchestration, multimodal perception and interaction, and multi-turn professional dialogue. To enable trajectory-aware grading, each run is recorded through three independent evidence channels: execution traces, audi…

2. Très proche Pas pertinent

   ClawEnvKit: Automatic Environment Generation for Claw-Like Agents

   Xi-Rui Li, Ming Li, Ion Stoica et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 10 fois · Pas encore résumé

   Résumé scientifique

   Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that what is needed is not just a dataset, but an automated pipeline capable of generating diverse, verified environments on demand. To this end, we introduce ClawEnvKit, an autonomous generation pipeline that instantiates this formalism from natural language descriptions. The pipeline comprises three modules: (1) a parser that extracts structured generation parameters from natural language input; (2) a generator that produces the task specification, tool interface, and scoring configuration; and (3) a validator that enforces feasibility, diversity, s…

3. Proche Pas pertinent

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

   Ningyan Zhu, Huacan Wang, Jie Zhou et al. · 2026 · Artificial Intelligence · preprint, non relu par les pairs · cité 4 fois · Résumé IA disponible

   Résumé scientifique

   The rise of OpenClaw in early 2026 marks the moment when millions of users began deploying personal AI agents into their daily lives, delegating tasks ranging from travel planning to multi-step research. This scale of adoption signals that two parallel arcs of development have reached an inflection point. First is a paradigm shift in AI engineering, evolving from prompt and context engineering to harness engineering-designing the complete infrastructure necessary to transform unconstrained agents into controllable, auditable, and production-reliable systems. As model capabilities converge, this harness layer is becoming the primary site of architectural differentiation. Second is the evoluti…

4. Proche Cité par cet article Pas pertinent

   ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents

   Fan-Qing Meng, Ling-Xiao Du, Zi-Jian Wu et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 23 fois · Pas encore résumé

   Résumé scientifique

   Language-model agents are increasingly used as persistent coworkers that assist users across multiple working days. During such workflows, the surrounding environment may change independently of the agent: new emails arrive, calendar entries shift, knowledge-base records are updated, and evidence appears across images, scanned PDFs, audio, video, and spreadsheets. Existing benchmarks do not adequately evaluate this setting because they typically run within a single static episode and remain largely text-centric. We introduce \bench{}, a benchmark for coworker agents built around multi-turn multi-day tasks, a stateful sandboxed service environment whose state evolves between turns, and rule-b…

5. Proche Cité par cet article Pas pertinent

   MetaClaw: Just Talk - An Agent That Meta-Learns and Evolves in the Wild

   Peng Xia, Jian-Wen Chen, Xin-Yu Yang et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 33 fois · Pas encore résumé

   Résumé scientifique

   Large language model (LLM) agents are increasingly used for complex tasks, yet deployed agents often remain static, failing to adapt as user needs evolve. This creates a tension between the need for continuous service and the necessity of updating capabilities to match shifting task distributions. On platforms like OpenClaw, which handle diverse workloads across 20+ channels, existing methods either store raw trajectories without distilling knowledge, maintain static skill libraries, or require disruptive downtime for retraining. We present MetaClaw, a continual meta-learning framework that jointly evolves a base LLM policy and a library of reusable behavioral skills. MetaClaw employs two co…

6. Proche Cité par cet article Pas pertinent

   SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

   Zi-Yu Ma, Shidong Yang, Yuxiang Ji et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 77 fois · Pas encore résumé

   Résumé scientifique

   Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are repeatedly rediscovered across users, preventing the system from improving with experience. While interactions from different users provide complementary signals about when a skill works or fails, existing systems lack a mechanism to convert such heterogeneous experiences into reliable skill updates. To address these issues, we present SkillClaw, a framework for collective skill evolution in multi-user agent ecosystems, which treats cross-user and over-time inter…

7. Proche Cite cet article Pas pertinent

   ClawLoop: Self-Improving Agents via Harness-Native Training Loop

   Han-Si Yang, Lin-Ji Hao, Hong-Yan Hao et al. · 2026 · Pas encore résumé

   Résumé scientifique

   The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents operate in sandbox workspaces and interact directly with file systems and shells. While numerous post-training pipelines exist for tool-use agents, their counterparts for harness-based agents remain scarce and are predominantly one-shot and teacher-dependent: a stronger external model synthesizes tasks and collects trajectories, the target agent is trained once, and evaluation results are consumed by human researchers rather than fed back into the loop. Such pipelines are inherently bounded by the capability of the external model and the scope …

8. Proche Pas pertinent

   EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions

   Jin-Cheng Zhong, Weizhi Wang, Che Jiang et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 2 fois · Pas encore résumé

   Résumé scientifique

   Enterprise agents increasingly operate inside workspaces: they read heterogeneous files, invoke tools, and deliver business artifacts. We introduce EnterpriseClawBench, an enterprise agent benchmark constructed from proprietary, real-world agent sessions. Starting from a large archive of workplace sessions, the EnterpriseClawBench produces 852 reproducible tasks, each paired with recovered fixtures, rewritten prompts, role classes, skill subclasses, hard rules, and semantic rubrics. Because the sessions contain internal enterprise content, we do not release the benchmark data; instead, our reusable contribution is the construction and evaluation protocol. On EnterpriseClawBench, the best con…

Les travaux antérieurs sur lesquels il s’appuie

1. Proche Pas pertinent

   SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

   Hua-Tong Song, Lisheng Huang, Shu'ang Sun et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 20 fois · Pas encore résumé

   Résumé scientifique

   In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline, including teacher-trajectory synthesis and data curation, long-horizon SFT, RL with real execution feedback, and inference framework design. Starting from an open-source base model with limited initial SWE capability, SWE-Master demonstrates how systematical optimization method can elicit strong long-horizon SWE task solving abilities. We evaluate SWE-Master on SWE-bench Verified, a standard benchmark for realistic software engineering tasks. Under identica…

2. Apparenté Pas pertinent

   Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale

   Rogerio Bonatti, Dan Zhao, Francesco Bonacci et al. · 2024 · International Conference on Machine Learning · cité 234 fois · Pas encore résumé

   Résumé scientifique

   Large language models (LLMs) show remarkable potential to act as computer agents, enhancing human productivity and software accessibility in multi-modal tasks that require planning and reasoning. However, measuring agent performance in realistic environments remains a challenge since: (i) most benchmarks are limited to specific modalities or domains (e.g. text-only, web navigation, Q&A, coding) and (ii) full benchmark evaluations are slow (on order of magnitude of days) given the multi-step sequential nature of tasks. To address these challenges, we introduce the Windows Agent Arena: a reproducible, general environment focusing exclusively on the Windows operating system (OS) where agents ca…

3. Apparenté Pas pertinent

   SWE-World: Building Software Engineering Agents in Docker-Free Environments

   Shu'ang Sun, Hua-Tong Song, Lisheng Huang et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 24 fois · Pas encore résumé

   Résumé scientifique

   Recent advances in large language models (LLMs) have enabled software engineering agents to tackle complex code modification tasks. Most existing approaches rely on execution feedback from containerized environments, which require dependency-complete setup and physical execution of programs and tests. While effective, this paradigm is resource-intensive and difficult to maintain, substantially complicating agent training and limiting scalability. We propose SWE-World, a Docker-free framework that replaces physical execution environments with a learned surrogate for training and evaluating software engineering agents. SWE-World leverages LLM-based models trained on real agent-environment inte…

4. Apparenté Pas pertinent

   Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey

   Jia-Cheng Zhu, Menghui Zhu, Renting Rui et al. · 2025 · arXiv.org · preprint, non relu par les pairs · cité 19 fois · Pas encore résumé

   Résumé scientifique

   The advent of large language models (LLMs), such as GPT, Gemini, and DeepSeek, has significantly advanced natural language processing, giving rise to sophisticated chatbots capable of diverse language-related tasks. The transition from these traditional LLM chatbots to more advanced AI agents represents a pivotal evolutionary step. However, existing evaluation frameworks often blur the distinctions between LLM chatbots and AI agents, leading to confusion among researchers selecting appropriate benchmarks. To bridge this gap, this paper introduces a systematic analysis of current evaluation approaches, grounded in an evolutionary perspective. We provide a detailed analytical framework that cl…

5. Apparenté Pas pertinent

   OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

   Tianbao Xie, Danyang Zhang, Ji-Xuan Chen et al. · 2024 · Neural Information Processing Systems · cité 1 437 fois · Pas encore résumé

   Résumé scientifique

   Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing accessibility and productivity. However, existing benchmarks either lack an interactive environment or are limited to environments specific to certain applications or domains, failing to reflect the diverse and complex nature of real-world computer use, thereby limiting the scope of tasks and agent scalability. To address this issue, we introduce OSWorld, the first-of-its-kind scalable, real computer environment for multimodal agents, supporting task setup, execution-based evaluation, and interactive learning across vari…

Les articles qui le citent

1. Proche Utilise cet article en profondeur Pas pertinent

   Scaling Verifiable Environments for Long-horizon Work Agents

   Jia-Zheng Zhang, Long Ma, Yun-Xian Yang et al. · 2026 · Pas encore résumé

   Résumé scientifique

   Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long-horizon interaction and trustworthy verification. However, hand-crafted environments incur prohibitive engineering overhead that prevents environment scaling, whereas synthesis methods sacrifice workspace complexity, realism, or grounded verifiability. To bridge this gap, we introduce WorkForge, a scalable synthesis framework for constructing verifiable work-agent environments from real-world resources. Starting from expert workflows, WorkForge first identifies the resources, decisions, and deliverables required by each workflow. It then retrieves rel…

2. Proche Pas pertinent

   WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution

   Hang He, Lin-Ting Wang, Guan-Ming Liu et al. · 2026 · Pas encore résumé

   Résumé scientifique

   Scaling interactive environments is important for training long-horizon agents through reinforcement learning. These environments often require further testing and refinement after initial generation, and correcting defects in a task may also require updating its work context and verifier. However, existing construction pipelines offer limited support for such iterative refinement while keeping these components aligned. We introduce WorkRover, a framework for training long-horizon cowork agents through recursive environment evolution. Its harness-driven synthesis enables construction agents to jointly build and validate semantically aligned work contexts, executable tasks, and evidence-groun…

3. Apparenté Utilise cet article en profondeur Pas pertinent

   Interlock: From Local Correctness to Task Completion in Long-Horizon Agents

   Lin-Ji Hao, Yan-Ji He, Zi-Han Wang et al. · 2026 · Pas encore résumé

   Résumé scientifique

   Large language model agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and dependencies across resources and artifacts. Existing agents may satisfy individual requirements while failing to maintain these relationships, producing locally correct but incomplete outcomes. These failures arise because task completion depends on relationships among environmental evidence, consequential decisions, and required effects. To address this completion gap, we propose Interlock, a framework for task synthesis that represents each task as a typed completion graph. Grounding edges connect public evidence to decisions, …

4. Proche Pas pertinent

   OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models

   Tian-Yi Lin, Chuan-da Sun, Jing-Yi Zhang et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 3 fois · Pas encore résumé

   Résumé scientifique

   Equipping Large Language Model (LLM) agents with effective skills is crucial for solving complex tasks in real-world systems like OpenClaw. In this work, we aim to develop a framework that automatically constructs such reusable skills to enhance LLMs in tool use, multi-step reasoning, and dynamic environment interaction. To this end, we propose Collective Skill Tree Search (CSTS), a novel tree-search-based skill construction framework that constructs structured, diverse and generalizable tree of skills. The core idea of CSTS is to leverage collective intelligence to jointly search, identify and compose effective skills via two iterative phases: Collective Skill Node Generation (CSN-Gen) and …

5. Apparenté Pas pertinent

   JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

   Gui-Bin Zhang, Leo Lu, Fang-Zhou Xie et al. · 2026 · cité 17 fois · Pas encore résumé

   Résumé scientifique

   Agent capability is not determined by the model alone. The agent harness, encompassing memory management, planning strategy, action protocol, and tool/skill orchestration, can dominate the contribution of the underlying foundation model. Yet harness design remains manual, task-specific, and fundamentally unscalable. We present JIT-Agent, a harness intelligence model trained to synthesize task-adaptive agent harnesses on the fly for arbitrary off-the-shelf agentic LLMs. We formalize the agent harness as a composable, machine-generatable artifact governed by a fixed four-module protocol, and train JIT-Agent to customize harnesses for a given task at hand, repair harnesses for stable and reliab…