- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper introduces TSADB, a database agent that uses schema information, query intent, execution history, and errors to build a state for choosing tools. A frozen LLM then generates the tool arguments. The authors test it on BIRD, Spider 2.0-Lite, and DS-Bench, alongside studies of rewards, controllers, robustness, and transfer to help explain the gains. The results show gains under matched interfaces and budgets, with the largest reported benefits on tasks requiring many tool calls.
Critical strengths
-
The experiments separate the effects of the state representation, reward, and controller to make it much easier to see where the gains come from.
-
TSADB beats RL-ReAct by 7.9 points on BIRD with the same training budget. The paper also makes clear how adapting the baseline interfaces affects their results.
Critical weaknesses
- The paper does not specify how the reward relevance projection is trained during warmup, including its objective and update rule. This omission limits reproducibility of the progress-reward component.
- The recovery procedure is not clearly distinguished from the standard interaction loop, making the reported 6.7 point ablation gain difficult to interpret. The tool masks and validation rules also require a more complete description.
Questions for authors
- Please specify the training objective and update rule for the reward relevance projection during warmup. Is this phase included in the 2,000 episode training budget?
- Please clarify how the recovery procedure differs from the standard interaction loop and what its ablation removes. Please also provide the complete tool-masking and validation rules, including the treatment of valid empty results.
- Please describe the task and database splits used for adaptation and evaluation, including their separation from model selection. What data and training budget are used for the full-retraining reference?
Respond for Reviewer anQ5 [Part 1/2]
Thank you for proposing a controller that uses the structured information directly as text (W2 and Q2).
Structured-input text router: At each step, we serialize the four information sources used by TSA: revealed schema and foreign-key relations, the current request/intent, the last ten action-observation summaries, and cumulative twelve-category error counts plus the latest error. Frozen GPT-5 receives this structured text and the same tool-validity mask, selects one of the five tools, and then generates arguments.
The comparison uses the same tool interface and a 20-action allowance covering tool executions and argument-regeneration retries. Additional LLM routing prompts are charged to the 120-second wall-clock limit and token/latency measurements; they do not consume tool-action slots. This preserves the action horizon while exposing the text router's inference cost.
Providing structured information to the text router improves over ReFoRCE by 2.4 points overall and 8.1 on long tasks. The supervised TSA controller reaches similar accuracy with 40% lower total per-step latency. PPO-based TSADB exceeds the text router by 7.6 points overall and 13.8 on long tasks, also at 40% lower total per-step latency.
This result supports the complete learned-control design. The policy ladder provides the comparison within the TSA architecture: PPO versus supervised control improves long-task EX by 13.1 points. We have presented the complementary comparisons in Section 5.5 (pp. 8–9) and Table 5 (p. 9). Appendix B.7 (p. 23) and Table 12 (p. 23) specify the serialization and budget accounting.
State by workflow scaffold (W4): We jointly removed tool masking, the adaptive loop, and argument validation, retaining the specified training reward:
The TSA effect is 8.6 points without the scaffold and 9.1 with it. On long tasks, the effects are 15.1 and 18.5 points. The corresponding differences-in-differences are +0.5 overall and +3.4 on long tasks. State organization improves completion in both scaffold conditions, with a larger interaction on long tasks. We have added this joint intervention in Table 14 (p. 24), alongside the individual ablations in Table 22 (p. 31).
Trace window and inference horizon (W3): With trace-window sizes K=5,10,15,20, overall BIRD EX is 79.8%, 82.0%, 82.2%, and 82.1%. Gains beyond ten pairs are small in this sweep; cumulative schema and error summaries remain available separately from the trace window.
On the same 85 long tasks, TSADB achieves 44.7%, 60.3%, and 63.5% EX with inference caps H=15,20,30. ReFoRCE reaches 38.4% at H=20 and 39.8% at H=30. These results distinguish the selected twenty-call operating point from performance with a larger inference allowance. The long-task group is defined by canonical reference horizon, independently of the evaluated cap.
Interface scope: The submitted experiments also cover Python execution through the DS-Bench interface, where the gain is 9.9 percentage points in TSR, and official c-Interact conversation, where the gain over RL-ReAct is 7.6 points. Larger and dynamically changing action spaces remain a useful extension of the five-tool controller. We have collected the window and horizon sweeps in Table 15 (p. 24) and discuss the interface scope in Section 6 (p. 10).