# Learning after Execution with Action-Specific Credit

arXiv: https://arxiv.org/abs/2610.14573 · HTML: https://mlsanity.com/paper/2610.14573/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 10 Oct 2026.

## Builds on (most cited first, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement](https://mlsanity.com/paper/2402.14658/) (2024)
- [Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering](https://mlsanity.com/paper/2403.03163/) (2024)
- [RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning](https://mlsanity.com/paper/2410.02089/) (2024)
- [ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation](https://mlsanity.com/paper/2406.09961/) (2024)
- [RLTF: Reinforcement Learning from Unit Test Feedback](https://mlsanity.com/paper/2307.04349/) (2023)
- [StarVector: Generating Scalable Vector Graphics Code from Images and Text](https://mlsanity.com/paper/2312.11556/) (2023)
- [AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ](https://mlsanity.com/paper/2310.00367/) (2023)
- [IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers](https://mlsanity.com/paper/2304.14400/) (2023)
- [Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback](https://mlsanity.com/paper/2403.16792/) (2024)
- [TikZero: Zero-Shot Text-Guided Graphics Program Synthesis](https://mlsanity.com/paper/2503.11509/) (2025)
- [Image2Struct: Benchmarking Structure Extraction for Vision-Language Models](https://mlsanity.com/paper/2410.22456/) (2024)
- [Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization](https://mlsanity.com/paper/2511.14846/) (2025)
- [MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching](https://mlsanity.com/paper/2601.10712/) (2026)
- [TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning](https://mlsanity.com/paper/2603.03072/) (2026)
- [Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation](https://mlsanity.com/paper/2603.17508/) (2026)

## Abstract (arXiv)

Execution is often used as terminal feedback: it scores a generated program, but the resulting state is not used for another learning action. Learning after execution instead uses the execution result as an intermediate state that supports an additional learning interaction for the same policy. This creates a credit-assignment problem because the two actions share the same final objective but play different roles in the trajectory. Accordingly, action-specific credit assigns the initial action credit from the final trajectory outcome and the corrective action credit for improvement over the intermediate state. Image-to-TikZ serves as an executable visual testbed for this setting. On 945 held-out examples, learning after execution strengthens the shared policy under single-call inference and also produces a post-execution corrective capability. Single-call render success reaches 92.70%, compared with 88.25% for continued single-stage GRPO after the same number of additional training iterations. This corrective capability is not reproduced by continued single-stage training and depends on the intermediate state. Alternative credit definitions also induce different group-relative preferences over the same trajectories. Together, these results suggest that executable tasks contain useful learning structure beyond a terminal reward. Code is available at https://github.com/tianyufengcn/Learning-after-Execution.