cs.AIAug 18, 2026
SaveWuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents
Abstract
Browser agents perform well on short, clean demonstrations, but real deployment is fundamentally different: agents must sustain dozens of decisions on live websites while recovering from mistakes and navigating complex UIs. We argue that closing this gap requires alignment at every level of the pipeline, including execution, supervision, optimization, and evaluation, rather than scale alone. We present Wuying-Browser-Agent, a unified framework that addresses each of these levels. A structured browser harness provides stable execution primitives and decision-oriented context management. Reflection and UI-specialized Curriculum SFT (RUIC-SFT) explicitly trains on recovery trajectories and complex-UI interactions. Divergence-Aware Online GRPO (DAO-GRPO) improves long-horizon credit assignment through potential-based reward shaping and divergence-aware step weighting. Finally, we introduce BrowserBench, a bilingual real-web benchmark of 350 tasks averaging 37.9 steps, because most existing benchmarks are too short to expose long-horizon failure modes. Wuying-Browser-Agent-27B achieves 80.6% on WebVoyager, 66.7% on Online-Mind2Web, and 65.1% on BrowserBench, establishing a new open-source state of the art on browser-use benchmarks. The same pipeline also transfers beyond browser use, demonstrating strong general agentic ability and reaching an average score of 73.8 on Tau2-Bench, Claw-Eval, and BFCL-v4.
Figures & tables
Figure 1: Performance comparison on online browser-use benchmarks and general agentic benchmarks.
Figure 2: Three structural challenges for browser agents in the long-horizon regime, and our co-designed solution. (a) Training data is dominated by successful trajectories, but real long-horizon execution routinely involves mistakes and detours, leaving recovery and complex-UI behavior weakly supervised. (b) Long browser trajectories often share long prefixes and differ at only a few decisive branch steps, so uniform trajectory-level optimization dilutes the learning signal. (c) Existing benchmarks underrepresent bilingual long-horizon real-web tasks, leaving the deployment regime we target insufficiently evaluated.
Figure 3: Overview of the Wuying-Browser-Agent pipeline. A shared browser harness layer supports two-stage policy training, with RUIC-SFT learning from around 3K curated trajectories and DAO-GRPO refining the policy through over 5K live-web rollouts. BrowserBench provides bilingual long-horizon evaluation, while a self-reinforcing data flywheel feeds verified interaction outcomes back into subsequent training.
| Category | Representative Actions |
|---|---|
| Navigation | go_to_url , search , go_back , switch_tab , close_tab |
| Interaction | click , hover , input , scroll , select_dropdown , drag , set_slider , upload , send_keys |
| Extraction | extract , screenshot , save_pdf , eval_javascript |
| File Operations | read_file , write_file |
| Flow Control | update_plan , load_skill , wait , done |
Table 1: Browser Agent Action Space. We define a structured browser action space with 24 atomic operations used in both SFT and online RL training. Actions are organized into five functional categories, including navigation, interaction, extraction, file operations, and flow control.
Figure 4: Piecewise linear annealing schedule for dataset mixing in RUIC-SFT. Training begins with a general-data-dominant distribution to stabilize basic browser operations, gradually increases the proportion of specialized UI component data to strengthen complex interaction skills, and introduces reflection data only in the late stage to cultivate self-correction without destabilizing the execution prior.
Figure 5: System overview of the online reinforcement learning stage. A task is sampled from the task pool and assigned to the browser agent controller, which interacts with multiple AgentBay sandboxes in parallel. Each sandbox produces one rollout trajectory, and the resulting trajectory group is consumed by the DAO-GRPO optimization module. The same GPU backend supports both policy serving during rollout and parameter updates during online optimization.
Figure 6: Overview of BrowserBench. BrowserBench contains 350 bilingual real-web tasks spanning 254 websites, with an average completion length of 37.9 steps. The benchmark covers eight task categories across Chinese and English websites, and each case is normalized into a goal-only instruction paired with a structured success criterion, enabling reliable Pass@1 evaluation of long-horizon browser agents.
| Model Name | WebVoyager | Online-Mind2Web | BrowserBench | Average |
|---|---|---|---|---|
| Closed-Source Models | ||||
| GPT-4o | 48.7 | 27.9 | 22.0 | 32.9 |
| GPT-5 | 80.1 | 67.1 | 61.7 | 69.6 |
| GPT-5.5 | 85.1 | 74.7 | 67.4 | 75.7 |
| Ernie-5.0 (>1T) | 51.9 | 31.3 | 24.9 | 36.0 |
| Qwen3.7-Plus | 73.6 | 60.1 | 59.4 | 64.4 |
Table 2: Task success rates (%) on three open-web benchmarks: WebVoyager, Online-Mind2Web, and BrowserBench. All models are evaluated with a maximum budget of 100 interaction steps. The Average column is the arithmetic mean of the three benchmarks. The best result in each column is shown in bold, and the second-best is underlined.
| Model | Tau2-Bench | Claw-Eval (Avg 3) | Claw-Eval (Pass 3 ) | BFCL-v4 | Average |
|---|---|---|---|---|---|
| Browser Agents | |||||
| OpenCUA 72B | 14.4 | 26.4 | 0.5 | 28.3 | 17.4 |
| GUI-Owl-1.5-32B-Instruct | 6.1 | 29.6 | 5.5 | 32.7 | 18.5 |
| UI-Venus-1.5-30B-A3B | 22.7 | 30.6 | 5.5 | 19.8 | 19.7 |
| EvoCUA-32B-20260105 | 48.9 | 46.3 | 6.5 | 48.8 | 37.6 |
| General Models | |||||
Table 3: Agentic performance comparison on selected benchmarks. We report performance on Tau2-Bench, Claw-Eval, and BFCL-v4 to evaluate whether browser-grounded training preserves broader tool-use and autonomous-agent capability beyond browser-specific tasks.
| # | Variant | Data Sources | Schedule | SR (%) | Recov. SR (%) | Steps | ||
|---|---|---|---|---|---|---|---|---|
| 1 | Base SFT | {\color[rgb]{0,0.5898,0}\checkmark} | {\color[rgb]{0.7852,0,0}\times} | {\color[rgb]{0.7852,0,0}\times} | None | 32.0 | 8.5 | 24.8 |
| 2 | +UI | {\color[rgb]{0,0.5898,0}\checkmark} | {\color[rgb]{0,0.5898,0}\checkmark} | {\color[rgb]{0.7852,0,0}\times} | Fixed | 34.9 | 9.0 | 23.1 |
| 3 | +Reflection | {\color[rgb]{0,0.5898,0}\checkmark} | {\color[rgb]{0.7852,0,0}\times} | {\color[rgb]{0,0.5898,0}\checkmark} | Fixed | 35.5 | 16.4 | 27.6 |
| 4 | +UI+Reflection | {\color[rgb]{0,0.5898,0}\checkmark} | {\color[rgb]{0,0.5898,0}\checkmark} | {\color[rgb]{0,0.5898,0}\checkmark} | Fixed | 36.6 | 17.1 | 29.3 |
| 5 | RUIC-SFT (full) | {\color[rgb]{0,0.5898,0}\checkmark} | {\color[rgb]{0,0.5898,0}\checkmark} | {\color[rgb]{0,0.5898,0}\checkmark} | Curriculum | 38.0 | 18.5 | 22.4 |
Table 4: Ablation on RUIC-SFT. All variants use the same 9B backbone and are evaluated on BrowserBench. “Fixed” applies a fixed multi-source mixture uniformly throughout training, while “Curriculum” uses the phased schedule. SR: overall task success rate; Recov. SR: erroneous-step recovery rate; Steps: average number of actions per completed task.
| Variant | PBRS | Div. Credit | Resp.-Level | SR (%) | Hard SR (%) | Recov. SR (%) |
|---|---|---|---|---|---|---|
| Vanilla Online GRPO | {\color[rgb]{0.7852,0,0}\times} | {\color[rgb]{0.7852,0,0}\times} | {\color[rgb]{0.7852,0,0}\times} | 39.4 | 23.8 | 24.8 |
| +PBRS | {\color[rgb]{0,0.5898,0}\checkmark} | {\color[rgb]{0.7852,0,0}\times} | {\color[rgb]{0.7852,0,0}\times} | 40.7 | 25.7 | 26.2 |
| +PBRS+Div. Credit | {\color[rgb]{0,0.5898,0}\checkmark} | {\color[rgb]{0,0.5898,0}\checkmark} | {\color[rgb]{0.7852,0,0}\times} | 41.9 | 27.6 | 29.7 |
| DAO-GRPO (full) | {\color[rgb]{0,0.5898,0}\checkmark} | {\color[rgb]{0,0.5898,0}\checkmark} | {\color[rgb]{0,0.5898,0}\checkmark} | 42.9 | 30.5 | 32.8 |
Table 5: Ablation on DAO-GRPO components. All variants are initialized from the same RUIC-SFT checkpoint and trained for the same number of online iterations. SR: overall task success rate; Hard SR: success rate on hard BrowserBench tasks; Recov. SR: success rate on recovery-oriented tasks.
Figure 7: Reliability of the LLM-based divergence estimator. (a) Agreement between estimator outputs and human annotation on 100 labeled rollout groups: exact / 1-step / 2-step localization of and favorable–unfavorable branch partition. (b) BrowserBench success rate of DAO-GRPO (9B) when the detected is randomly perturbed by up to 2 or 4 steps or replaced by a random step; the dashed line marks the uniform-credit variant (+PBRS, 40.7%) from Table 5 .
Figure 8: Online RL training dynamics of Wuying-Browser-Agent-9B. (a) Shaped reward on training batches (per-step scatter with moving average) and on a held-out validation split, the latter also reported over valid rollouts only. (b) Invalid-action ratio on the training and validation environments throughout online RL. (c) Fraction of rollout groups with zero reward variance in each iteration; these groups contribute no relative-advantage signal and are masked by dynamic sampling. The dashed line marks the training average of 26.7%. (d) Final success rate under different training budgets (up to 150 iterations) and parallel sandbox concurrency levels. Overall, online optimization improves both reward and action validity, degenerate groups persist throughout training and are handled by dynamic sampling, and higher sandbox concurrency yields better final performance under the same number of update steps.
Figure 9: Success rate by task difficulty (a) and (b) trajectory length in steps on 9B model backbone. Trajectory length is binned into four ranges: 15–25, 26–35, 36–50, and 50 steps.
Figure 10: Real rollout groups from online RL training, illustrating the three design choices of DAO-GRPO. For analysis we sample 16–20 rollouts per task (beyond the training group size ) and display six representative ones per group; row ends show final rewards, and the bottom strips show the mean per-step PBRS shaped reward of the displayed rollouts. (a) A Galaxy Z Fold7 browsing group: all rollouts share an identical three-step prefix (shaded corridor) and diverge at into top-down browsing ( : scroll ) vs. anchor jumping ( : scroll_to_text ); 12 of 16 browsing rollouts succeed while 3 of 4 jumping rollouts stall at partial credit, and progress credit concentrates on the post-divergence steps of the favorable branch. (b) A Galaxy S23 Ultra group in which 16 of 17 rollouts fail with returns : under terminal-only rewards the group would be degenerate (advantage ), whereas PBRS progress increments keep the rollouts correctly ordered ( ). (c) An accessory-filtering group in which 12 of 16 rollouts all reach reward with lengths from 21 to 49 steps; signed PBRS increments penalize individual detour steps (crosses; deep dots: credited steps; light dots: no credit), e.g. 14 consecutive penalized steps in R5, separating efficient from wasteful executions that identical terminal rewards cannot distinguish.
Figure 11: Self-reflective error recovery in long-horizon web navigation. A 15-step trajectory of Wuying-Browser-Agent-9B on a Chery privacy-policy retrieval task. The agent detects an erroneous redirect from the observed browser state, performs corrective recovery, and escalates from scrolling to structured probing before reaching the personal information collection list. For ease of visualization, we display screenshots for all steps to highlight interface transitions; in actual deployment, the agent primarily consumes structured browser state (e.g., DOM-derived representations), while screenshots are used only as optional inputs when visual grounding is needed.
More in this topic
Web Agents
Web agents use language and vision models to navigate websites, gather information, and complete tasks through interactive interfaces.
See all 174 papers