ClawGym: A Scalable Framework for Building Effective Claw Agents

• URL: http://arxiv.org/abs/2604.26904v1
• Date: Wed, 29 Apr 2026 17:12:22 GMT
• Title: ClawGym: A Scalable Framework for Building Effective Claw Agents
• Abstract summary: We present ClawGym, a scalable framework that supports the full lifecycle of Claw-style personal agent development.<n>ClawGym-SynData is a dataset of 13.5K filtered tasks synthesized from persona-driven intents and skill-grounded operations.<n>We then train a family of capable Claw-style models, termed ClawGym-Agents, through supervised fine-tuning on black-box rollout trajectories.<n>We further construct ClawGym-Bench, a benchmark of 200 instances through automated filtering and human-LLM review.
• Score: 47.47444724291439
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 verification mechanisms. We then train a family of capable Claw-style models, termed ClawGym-Agents, through supervised fine-tuning on black-box rollout trajectories, and further explore reinforcement learning via a lightweight pipeline that parallelizes rollouts across per-task sandboxes.To support reliable evaluation, we further construct ClawGym-Bench, a benchmark of 200 instances calibrated through automated filtering and human-LLM review. Relevant resources will be soon released at https://github.com/ClawGym.

Related papers

• EnvCraft: Synthesizing Executable Environments in Agentic RL for Claw-like Agent [21.572853994120806]
  EnvCraft is an automated framework for synthesizing executable environments and scalable training data.<n>We synthesize 139 interactive environments comprising approximately 20K complex tasks for Agentic RL training.
  arXiv  Detail & Related papers  (2026-09-04T10:13:41Z)
• ClawGym II: Exploring Black-Box RL on Agent Harness [82.92963070856416]
  Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment.<n>We present a unified black-box RL framework for stable and scalable optimization of general agents through complex harnesses.
  arXiv  Detail & Related papers  (2026-08-17T16:53:03Z)
• ClawRec: A Claw-Native Recommender System [70.37279331430653]
  We introduce Claw-native recommender systems, which move beyond platform-local ranking to produce unified, complementary recommendation slates spanning diverse sources and content forms.<n>ClawRec maintains an evidence-linked, temporally structured user state that connects cross-platform behaviors with cross-source recommendations.<n>Experiments show that ClawRec outperforms the strongest baselines, achieving an NDCG@20 of 0.6134 (+0.1126) and a Hit@20 of 0.6944 (+0.0854)
  arXiv  Detail & Related papers  (2026-07-26T17:56:49Z)
• KAT-Coder-V2.5 Technical Report [61.907486544595336]
  KAT-Coder-V2.5 is a coding-focused agentic model trained to act autonomously inside real, executable repositories.<n>It reconstructs multilingual repositories into sandboxed environments with fail-to-pass and pass-to-pass verification at scale.<n>We further scale reinforcement learning with harness randomization, a reliability-hardened sandbox, an asymmetric actor--critic PPO with hindsight-augmented value estimation, and a harness-oriented reward framework.
  arXiv  Detail & Related papers  (2026-07-06T08:14:02Z)
• ClawEnvKit: Automatic Environment Generation for Claw-Like Agents [85.29126619772153]
  We introduce ClawEnvKit, an autonomous generation pipeline capable of generating verified environments on demand.<n>ClawEnvKit comprises three modules: (1) a pipeline 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, structural validity, and internal consistency.<n>We construct Auto-ClawEval, the first large-scale benchmark for claw-like agents, comprising 1,040 environments across 24 categories.
  arXiv  Detail & Related papers  (2026-04-20T17:36:49Z)
• MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild [74.7263562191605]
  Large language model (LLM) agents are increasingly used for complex tasks.<n>Existing methods either store raw trajectories without distilling knowledge, maintain static skill libraries, or require disruptive downtime for retraining.<n>We present MetaClaw, a continual meta-learning framework that jointly evolves a base LLM policy and a library of reusable behavioral skills.
  arXiv  Detail & Related papers  (2026-03-17T22:30:30Z)
• Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem [90.17610617854247]
  We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimize the production pipeline for agentic model.<n>ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering.<n>We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories.
  arXiv  Detail & Related papers  (2025-12-31T14:03:39Z)
• CoRL: Environment Creation and Management Focused on System Integration [0.0]
  The Core Reinforcement Learning library (CoRL) is a modular, composable, and hyper-configurable environment creation tool. It allows minute control over agent observations, rewards, and done conditions through the use of easy-to-read configuration files, pydantic validators, and a functor design pattern.
  arXiv  Detail & Related papers  (2023-03-03T19:01:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.