- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies code-interactive reasoning for financial candlestick charts. It introduces FinKLine-32K, a dataset of replay-verified reasoning trajectories, FinKLineBench, a benchmark with 1,200 questions across 138 task types, and Fin-Thinker, a Qwen3.5-9B model trained with visual-code SFT, financial process supervision, and execution-feedback RL. Fin-Thinker achieves 53.2% answer accuracy and 43.1% grounded accuracy, outperforming the evaluated baselines.
Critical strengths
1.The task is well motivated. Financial chart questions often require locating evidence across dates and panels, and code interaction is a natural way to support this process.
2.The benchmark evaluates more than final-answer accuracy. Separating answer correctness, code execution, and evidence grounding makes the model’s behavior easier to diagnose.
Critical weaknesses
1.All main results are on the authors’ own benchmark. The unseen-task split is still within the same taxonomy, so it does not show transfer to independently collected financial chart benchmarks.
2.The paper does not establish that general visual tool-use or “thinking with images” ability transfers to financial charts. Stage I already includes financial chart tasks, while the base model performs worse with code access, so the gains from tool use and financial knowledge remain mixed together.
Questions for authors
1.How does Fin-Thinker perform on relevant subsets of existing financial chart benchmarks without additional training?
2.Can general visual tool-use models solve these financial chart tasks without financial process supervision, and how much do the different training stages contribute separately?
3.How much does the reference-aware teacher affect the reasoning patterns and final performance learned from FinKLine-32K?
9 comments
Response (Part 2)
W2/Q2: Can general visual-tool-use models solve these financial chart tasks without financial process supervision, and how much do the different training stages contribute separately?
We thank the reviewer for raising this important concern. We conduct three complementary analyses to distinguish the contributions of general visual-tool training, foundational financial chart skills, and financial process supervision: base-model evaluation with code access, Stage I data ablation, and supervision-format comparisons across training stages.
1. Base-model Performance with Code Access.
Qwen3.5-9B achieves 23.6% accuracy through direct answering, while its accuracy drops to 20.0% when code execution is enabled. This performance degradation suggests that image-grounded code reasoning in financial chart analysis is challenging for general-purpose models without task-specific training. It requires coordinating visual evidence extraction, date and indicator identification, code execution, and subsequent reasoning. Simply providing code execution access does not equip models with these capabilities, motivating our staged training approach.
2. Separating General Visual-Tool Training from Basic Financial Skills.
To disentangle the contributions of general visual-tool training and task-specific financial chart skills, we conduct a Stage I data ablation. The 6,570 Stage I financial examples are not general financial knowledge . Instead, they are some atomic-tool trajectories for reading and interpreting candlestick charts, including extracting price and volume information, locating exact trading dates, identifying chart patterns and technical indicators, detecting MA5–MA10 crossovers, and counting price-rise and volume-expansion days. These examples teach foundational operations for acquiring and interpreting financial chart evidence, rather than complete multi-step financial reasoning trajectories. We compare three Stage I configurations: General TWI Only (13,910 examples), Basic Financial Skills Only (6,570 examples), and their combination (20,480 examples). all configurations subsequently use the same FinKLine-32K data in Stage II and the full execution-feedback reward in Stage III.
Table G2. Stage I data ablation on FinKLineBench (accuracy, %).
| Stage I data | Stage I | After Stage II | After Stage III |
|---|---|---|---|
| General TWI Only | 22.4 | 42.5 | 45.2 |
| Basic Financial Skills Only | 28.4 | 45.7 | 50.8 |
| General TWI + Basic Financial Skills (Ours) | 36.4 | 49.1 | 53.2 |
Adding basic financial skills to general TWI training raises Stage I accuracy from 22.4% to 36.4%. After all three stages, the financial-skills-only configuration reaches 50.8%, compared with 45.2% for the general-only configuration, while combining both sources achieves 53.2%. These results demonstrate complementary contributions from general visual-tool training and foundational financial chart skills. The substantial improvements after Stage II further demonstrate the additional value of full financial process supervision from FinKLine-32K.
3. Separating Supervision Formats Across Training Stages.
We further compare Answer-only, Textual CoT, Code (6K), and Code (Full) across training stages. All variants are based on Qwen3.5-9B, whose base accuracy on FinKLineBench is 23.6%.
In Stage I, all variants use the same 6,570 foundational financial chart tasks but differ in supervision: Answer-only uses final-answer supervision, Textual CoT uses GPT-distilled reasoning, and Code (6K) uses corresponding atomic-tool trajectories to supervise chart-evidence operations, some without final answers. Code (Full) further adds 13,910 public TWI trajectories. In Stage II, all variants are trained on the same 32,184 FinKLine-32K instances under their respective supervision formats.
Table G3. Accuracy across training stages on FinKLineBench (additional evaluation, %).
| Training stage | Answer-only | Textual CoT | Code (6K) | Code (Full) |
|---|---|---|---|---|
| Stage II only (without Stage I) | 29.2 | 34.6 | — | — |
| Stage I | 25.0 | 26.3 | 28.4 | 36.4 |
| Stage I+II | 30.4 | 34.6 | 45.7 | 49.1 |
| Stage I + II + III (shared answer reward) | 31.1 | 36.7 | 48.7 | 51.7 |
| Stage I + II + III (full execution-feedback reward) | — | — | 50.8 | 53.2 |
Q3: What does the reference-aware teacher contribute to trajectory construction and final student performance?
We compare reference-free and reference-aware teacher guidance on the same 500 tasks, including 200 hard tasks, separately from the 690-task experiment in paper Table 5. The intervention is whether the teacher can access reference answers during offline correction.
Table G3. Reference-aware teacher ablation: trajectory construction.
| Metric | Reference-free | Reference-aware |
|---|---|---|
| Acceptance ↑ | 24.0% (120/500) | 73.0% (365/500) |
| Hard-task acceptance ↑ | 7.0% (14/200) | 59.0% (118/200) |
| Correction rounds ↓ | 3.6 | 2.1 |
The reference-aware teacher helps turn unsuccessful explorations into verified training trajectories, providing supervision on evidence acquisition and error recovery. On the same 500 tasks, reference access increases acceptance from 24.0% to 73.0%, and hard-task acceptance from 7.0% to 59.0%. The student generates the operations and corrections; teacher feedback and reference-answer inputs are excluded, and retained executions undergo independent replay.
Complementary evidence from the recovery-supervision ablation shows an accuracy improvement from 44.3% to 49.1% (paper Table 4C), supporting the downstream value of corrective trajectories.
Response (Part 1)
We sincerely thank you for your constructive feedback and recognition of our task motivation and process-aware evaluation. We appreciate your suggestions on cross-benchmark generalization, training-stage contributions, and reference-aware teacher guidance, and provide further evidence below.*
We agree that the Seen/Unseen split within FinKLineBench alone cannot establish cross-benchmark generalization.
We select a total of 100 candlestick-related objective questions from VisFinEval (Liu et al., 2025), FinChart-Bench (Shu et al., 2026), MME-Finance (Gan et al., 2025), and https://huggingface.co/datasets/qsWDFGHN/FIN-VQA A, and evaluate Fin-Thinker without additional training. This evaluation focuses on selected candlestick-related subsets of these external datasets, with all reported results referring to the same 100-question sample.
Table G1. Zero-additional-training evaluation on 100 external financial-chart questions (accuracy, %).
Fin-Thinker achieves 63.0%, outperforming Qwen3.5-9B (39.0%) and DeepEyesV2 (32.0%) by 24.0 pp and 31.0 pp, respectively, while remaining close to GPT-5.5 (64.0%) and Claude Opus 4.8 (66.0%) on this sample. Among the evaluated models, Fin-Thinker achieves the highest accuracy on MACD, Indicator, and Price–Volume, but trails GPT-5.5 and Claude Opus 4.8 on Pattern and Trend. These findings provide preliminary evidence of transfer to external financial-chart questions, while the evaluation remains limited to this 100-question sample.