CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents

Zhongwei Xie; Yiming Du; Jiaxin Bai; Baixuan Xu; Chunyang Li; Xiyu Ren; Wei Fan; Tianshi Zheng

cs.AIOct 18, 2026

CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents

Authors: Zhongwei Xie, Yiming Du, Jiaxin Bai, Baixuan Xu, Chunyang Li, Xiyu Ren, Wei Fan, Tianshi Zheng,

Organizations: The Hong Kong University of Science and Technology · The Chinese University of Hong Kong · Hong Kong Baptist University · Independent Researcher

Abstract

AI coworkers must coordinate tools, communicate across turns, and act on changing workspace state while respecting workflow constraints. Constructing training experience for these capabilities requires coherent requests, service records, tool interfaces, and grading checks. We present CoworkEnv, a capability-guided framework for synthesizing executable training environments for AI coworkers. Workflow requirements guide task construction, and programmatic validation with feedback repair checks generated specifications and grading behavior. Teacher executions yield curated demonstrations for supervised fine-tuning (SFT), while student interactions provide rollouts and rewards for reinforcement learning (RL). Using these resources, we train compact PocketWorker models. For Qwen3-VL-8B-Instruct, SFT raises the mean score from 46.6 to 64.1 on Claw-Eval, including a 31.9-point gain on Multi-turn tasks. An SFT-only extension to ClawMark demonstrates applicability across coworker benchmarks. We further compare RL training dynamics across configurations that vary reward processing and credit assignment. Improving training rewards provide preliminary evidence that the constructed environments support policy optimization.

Figures & tables

Figure 1: Task construction and the teacher-demonstration path. Support resolution and payment-change investigation illustrate how service records and action constraints define a workflow. Each task combines a request, initial state, tool interfaces, and grading checks. Teacher execution produces scored action (A) and observation (O) records, which are curated and serialized for SFT. The same task components support student interaction and online reward computation through the RL interface described in Section 3.4 .

Figure 2: Service coverage and task composition of the construction libraries. (a) Qualitative service and input coverage across both inventories, grouped by function. (b–c) Task families (inner rings) and subtypes (outer rings) for Claw-Eval (602 task identifiers) and ClawMark (263), with shared colors and labels for the largest sectors. The 236 shared identifiers are counted once in each inventory; totals are not additive. Counts describe construction-library snapshots, not benchmark test sizes or checkpoint training-set sizes.

Model	General [-1pt] $n=161$			Multi-turn [-1pt] $n=38$			Overall [-1pt] $n=199$
	Score	Pass@3	Pass 3	Score	Pass@3	Pass 3	Score	Pass@3	Pass 3
Claude Opus 4.6	80.6	80.8	70.8	79.6	89.5	68.4	80.4	82.4	70.4
Claude Sonnet 4.6	81.3	81.4	68.3	81.9	89.5	65.8	81.4	82.9	67.8
GPT 5.4	78.3	75.8	60.2	79.0	89.5	60.5	78.4	78.4	60.3
Gemini 3.1 Pro	76.6	80.8	55.9	80.2	92.1	65.8	77.3	82.9	57.8
MiMo V2 Pro	76.0	72.7	57.1	81.0	92.1	60.5	77.0	76.4	57.8

Table 1: Claw-Eval performance on General and Multi-turn tasks. Score, Pass@3, and Pass 3 use a 0–100 scale. Pass@3 and Pass 3 require at least one and all three trials to score

\geq 0.75

, respectively. Overall combines the two groups with equal weight per task. Published references reproduce Table 3 of Ye et al. [2026] . Parentheses show absolute changes from the same-size base model. Scores and changes are rounded separately to one decimal place. Darker cells indicate higher scores within each color group. Evaluation setup: Section 4.1 .

Model	Tasks	Score $\uparrow$
GPT-5.4	100	56.7
Claude Sonnet 4.6	100	53.1
Qwen3.6 Plus	100	48.7
Gemini 3.1 Pro Preview	100	38.9
MiniMax M2.7	100	33.0
Kimi K2.5	100	56.0

Table 2: ClawMark mean task scores (0–100). Website references use OpenClaw Run 1 over 100 tasks [ Evolvent AI, 2026b ] . Parentheses show absolute changes from Qwen3-VL-8B-Instruct. Protocol details appear in Appendix F .

Training condition	General [-1pt] $n=161$	Multi-turn [-1pt] $n=38$	Overall [-1pt] $n=199$	Multimodal [-1pt] $n=101$	All tasks [-1pt] $n=300$
Qwen3-VL-8B-Instruct	46.7	45.9	46.6	20.7	37.9
GRPO	52.8 -1pt	72.5 -1pt	56.6 -1pt	22.1 -1pt	45.0 -1pt
GDPO	53.0 -1pt	74.9 -1pt	57.2 -1pt	21.0 -1pt	45.0 -1pt
Dr.GRPO	51.2 -1pt	67.1 -1pt	54.3 -1pt	21.0 -1pt	43.1 -1pt
GiGPO	59.7 -1pt	64.8 -1pt	60.7 -1pt	21.0 -1pt	47.3 -1pt

Table 3: Claw-Eval results after supervised warm-up and RL. Scores on the 300-task benchmark use a 0–100 scale. Overall combines General and Multi-turn; All tasks also includes Multimodal. The General, Multi-turn, and Overall base scores are shared with Table 1 . Parentheses show absolute changes from Base for the warm-up-plus-RL pipeline. Scores and changes are rounded separately to one decimal place. Bold indicates the highest score in each column.

SFT data	General [-1pt] $n=161$	Multi-turn [-1pt] $n=38$	Overall [-1pt] $n=199$
Base (no SFT)	46.7	45.9	46.6
20%	50.1 -1pt	53.6 -1pt	50.8 -1pt
50%	53.4 -1pt	64.9 -1pt	55.6 -1pt
100% (full)	60.9 -1pt	77.8 -1pt	64.1 -1pt

Table 4: Claw-Eval scores (0–100) for Qwen3-VL-8B-Instruct with different SFT data fractions. The specified fraction is randomly sampled within each SFT stage; parentheses show gains over Base. Base and full-data scores are the three-trial results from Table 1 . Overall weights tasks equally. Scores and gains are rounded separately to one decimal place.

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 3 — Figure 3: Comparison of RL training methods on our constructed tasks. Rows show GRPO, GDPO, GiGPO, and Dr.GRPO; columns show training reward, policy loss, and response length over approximately three epochs. The horizontal axis counts cumulative processed training samples, including repeated sampling of a prompt across epochs. Curves are smoothed using a moving average over 8 logged steps.

Component	Generated tool workflows	Dialogue demonstrations
Task source	Coverage plans, generated specifications, and reusable services	Independently constructed dialogue scenarios and user personas
Interaction	An initial request followed by agent tool calls and service observations	A persona-based user simulator exchanges turns with the agent
Grading	Deterministic checks of tool calls, arguments, and audit records	An LLM judge evaluates clarification and final-answer quality
Preparation	Export execution records and convert them to student messages	Extract recorded dialogue trials, select demonstrations, and normalize messages

Appendix

Table 5: Preparation paths for tool-workflow and dialogue demonstrations collected on our constructed training tasks.

LLM Agent Training

Large language model agent training teaches models to plan, use tools, and learn from multi-step interaction with environments.

See all 586 papers

Cowork-Gym: Synthesizing Interactive Work Environments at Scale
Oct 13, 2026Anni Zou, Cheng Chen, Jiaji Deng +18Tool-Using Agents LLM Agent Training
Alibaba Token Foundry
WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution
Oct 13, 2026Hang He, Linting Wang, Guanming Liu +14LLM Agent Training Long-Horizon LLM Agents
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
Apr 26, 2026Fanqing Meng, Lingxiao Du, Zijian Wu +46Computer-Use Agent Benchmarks LLM Agent Evaluation

Oct 13, 2026J/K move · Enter open · S save

Cowork-Gym: Synthesizing Interactive Work Environments at Scale

Anni Zou, Cheng Chen, Jiaji Deng, Weikang Zhou+17

Alibaba Token Foundry

Tool-Using Agents LLM Agent Training

Open paper AskPDF arXiv

Cowork agents navigate dependencies across tools and files while adapting to changing user requirements and edits to shared workspaces. Scaling such environments requires maintaining consistency among task objectives, executable resources, user behavior, and success criteria. We introduce Cowork-Gym, a framework that synthesizes Cowork environments through a build-execute-revise loop that uses execution evidence and review feedback to validate and repair generated environments. To capture realistic Cowork dynamics, a stateful user simulator responds to the agent's actions through dialogue and direct edits to the shared workspace. We synthesize 64.9K environments across 14 application scenarios and use them to post-train 9B, 27B, and 35B-A3B Qwen models with supervised fine-tuning, reinforcement learning, and on-policy distillation. Averaged across six agentic benchmarks, these models outperform their corresponding base checkpoints by 8.7, 6.4, and 4.1 points, respectively. Ours-27B ranks second overall among the evaluated models and achieves the highest average scores on PawBench and ClawEval, outperforming models with over 100B total parameters on both benchmarks.

Abstract

LLM Agent Training

Explore similar work

Cowork-Gym: Synthesizing Interactive Work Environments at Scale

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

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