- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper studies a large planner paired with a smaller executor for coding and search agents. Executor GRPO updates only the executor, using the final task reward shared across its execution rounds while keeping the planner frozen. Training Qwen3.5-9B with a Hy3 planner improves both task scores and token use relative to the untrained executor. For example, SWE-bench Verified rises from 65.6 to 70.0 while executor tokens fall from 6.17M to 1.63M per task. Evaluations with two other planners and two search benchmarks test transfer. An open-data training variant, a monolithic-GRPO comparison, and response analyses provide additional evidence about the learned specialization.
Critical strengths
-
The improvement over the untrained executor is substantial and appears across planners and domains. The coding-to-search transfer is particularly useful evidence that the adaptation learns something beyond the training task interface.
-
Table 3 is an informative test of specialization: LiteExec performs worse alone but better under the planner. This supports the practical case for training an executor in its intended interaction setting. The cost analysis is also unusually candid about provider prices and caching; Appendix C reports a setting where the advantage over a monolithic model reverses.
Critical weaknesses
-
The architectural comparison is also restricted to a monolithic agent and a fixed sequential planner-executor arrangement. Why were other multi-agent variants not considered, such as an orchestrator that dynamically delegates to multiple or specialized workers, with parallel execution where appropriate?
-
How would ordinary GRPO perform if its reward jointly accounted for task success and inference cost? Would Executor GRPO still offer an advantage under this objective?
Questions for authors
please see Weaknesses 1 and 2
2 comments
Response to Reviewer QPni (Part 2)
How would ordinary GRPO perform if its reward jointly accounted for task success and inference cost? Would Executor GRPO still offer an advantage under this objective?
Thank you for suggesting this comparison. We agree that jointly optimizing task success and efficiency is another promising research direction. We appreciate the opportunity to investigate this approach and compare it with our method.
Evaluation with cost-aware GRPO. To investigate this approach, we use ShorterBetter (Yi et al., NeurIPS 2025), a GRPO method that encourages efficiency by jointly rewarding task correctness and penalizing deviations from the shortest successful response length. We train Qwen3.5-9B on the same training data as LiteExec, using α = 2 and β = 0.001 following the hyperparameter guidance in the paper, with eight rollouts per group. The reward is r = αs − β|L − L*|, where s is the task score, L is the trajectory length, and L* is the length of the shortest fully successful rollout in the group, or the mean length of valid rollouts if none fully succeeds. Further details of ShorterBetter can be found in the original paper.
Yi, J., Wang, J., and Li, S. (2025). ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning. Advances in Neural Information Processing Systems, 38.
Results and analysis. We evaluate the ShorterBetter GRPO checkpoints at 50 and 100 training steps as executors with Hy3 as the planner. All configurations use the same benchmark tasks and token prices. We report mean ± sample standard deviation across three evaluation runs. Estimated costs follow the calculation protocol in Table 1 of the paper and include both planner and executor calls.
| Executor / Training | SWE-bench Verified (% resolved) ↑ | Cost (USD/task) ↓ | SWE-bench Multilingual (% resolved) ↑ | Cost (USD/task) ↓ |
|---|---|---|---|---|
| Qwen3.5-9B | 66.4 ± 1.2 | 0.511 ± 0.009 | 59.8 ± 1.9 | 0.508 ± 0.019 |
| + ShorterBetter GRPO (50 steps) | 68.5 ± 1.2 | 0.290 ± 0.006 | 60.2 ± 1.3 | 0.320 ± 0.010 |
| + ShorterBetter GRPO (100 steps) | 67.4 ± 0.9 | 0.122 ± 0.004 | 59.7 ± 2.2 | 0.142 ± 0.001 |
| + Executor GRPO (LiteExec-9B) | 70.6 ± 1.0 | 0.160 ± 0.003 | 67.0 ± 0.9 | 0.186 ± 0.005 |
As shown in the table, ShorterBetter substantially reduces estimated costs, with further reductions from 50 to 100 training steps accompanied by lower mean task resolution rates on both benchmarks. Compared with the 50-step ShorterBetter checkpoint, LiteExec-9B achieves higher task resolution rates and lower estimated costs. Compared with the 100-step checkpoint, its performance advantage increases to 3.2 percentage points on SWE-bench Verified and 7.3 percentage points on SWE-bench Multilingual, at additional estimated costs of USD 0.038 and USD 0.044 per task, respectively. Executor GRPO (LiteExec) lies on the Pareto frontier among the evaluated configurations on both benchmarks, illustrating the trade-off between task resolution and cost in the collaborative setting. Although ShorterBetter jointly accounts for task success and efficiency, its objective remains centered on individual task-solving capability, while Executor GRPO (LiteExec) targets collaboration capability, such as the executor reporting execution evidence and clearly communicating blocked status to the planner. We believe that developing effective collaboration capabilities in agents, either with humans or with other agents, is a promising research direction beyond the prevailing emphasis on independent task solving.
Response to Reviewer QPni (Part 1)
Thank you for your thoughtful review. We appreciate your recognition of the strengths of our work and your suggestions for improving the paper. We have considered each of your comments and hope our responses below address your concerns.
Thank you for raising this point. We agree that evaluating a broader range of agent harnesses would be valuable, and we appreciate the opportunity to clarify why we chose a sequential setup for this study.
Why we chose a simple sequential setup. Our primary research question is whether a small model can serve as an executor and carry out most of the execution work in collaboration with a large model. The fundamental challenge is whether the small model can collaborate effectively, for example, by providing supporting evidence and clearly reporting whether it completed its assigned subtask. These requirements apply across agent harnesses, whether execution is sequential or parallel. We therefore use a simple sequential setup to focus on the executor’s ability to collaborate. Harnesses with multiple or specialized workers raise additional questions about how effectively the planner can assign work, coordinate workers with different capabilities, and resolve conflicts between their actions. These challenges primarily concern the planner’s orchestration capabilities. Given our focus on the executor, we leave a systematic evaluation of these settings for future work.
Evaluation with an additional agent harness. To further assess whether the benefits of executor training extend beyond the sequential setup, we implemented a harness variant that allows the planner to invoke multiple executors within a single round (with the planner prompt explicitly permitting parallel delegation). We compare Qwen3.5-9B and LiteExec-9B under concurrency limits of one (as in the paper), two, and four executors. The planner determines whether and when to delegate subtasks in parallel. We use Hy3 as the planner and the same benchmark tasks across settings, and report the mean and sample standard deviation across three evaluation runs for each setting.
Across all evaluated harness settings, LiteExec-9B achieves higher task resolution rates than the off-the-shelf Qwen3.5-9B executor on both benchmarks. These results suggest that the benefits of executor training extend beyond the sequential setup to a harness that supports parallel execution.