# Chain-of-Adaptation: Surgical Vision-Language Adaptation with Reinforcement Learning

arXiv: https://arxiv.org/abs/2603.20116 · HTML: https://mlsanity.com/paper/2603.20116/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 35 of its 39 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 35)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [The Curse of Recursion: Training on Generated Data Makes Models Forget](https://mlsanity.com/paper/2305.17493/) (2023)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation](https://mlsanity.com/paper/2401.04092/) (2024)
- [AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy](https://mlsanity.com/paper/2208.02049/) (2022)
- [Comparative Validation of Machine Learning Algorithms for Surgical Workflow and Skill Analysis with the HeiChole Benchmark](https://mlsanity.com/paper/2109.14956/) (2021)
- [Heidelberg Colorectal Data Set for Surgical Data Science in the Sensor Operating Room](https://mlsanity.com/paper/2005.03501/) (2020)
- [Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery](https://mlsanity.com/paper/2305.11692/) (2023)
- [Vision-Language Models Provide Promptable Representations for Reinforcement Learning](https://mlsanity.com/paper/2402.02651/) (2024)
- [The TUM LapChole dataset for the M2CAI 2016 workflow challenge](https://mlsanity.com/paper/1610.09278/) (2016)
- [EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery](https://mlsanity.com/paper/2501.11347/) (2025)
- [LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning](https://mlsanity.com/paper/2408.07981/) (2024)

## Abstract (arXiv)

Conventional fine-tuning on domain-specific datasets can inadvertently alter a model's pretrained multimodal priors, leading to reduced generalization. To address this, we propose Chain-of-Adaptation (CoA), an adaptation framework designed to integrate domain knowledge while maintaining the model's inherent reasoning and perceptual capabilities. CoA introduces a structured reasoning format that enhances domain alignment without sacrificing general multimodal competence by reinforcement learning. Experiments on standard surgical benchmarks, under both in-distribution and out-of-distribution settings, demonstrate that CoA achieves higher accuracy, stronger generalization, and more stable behavior than supervised fine-tuning. Furthermore, ablation studies confirm that CoA effectively preserves the model's core visual-language abilities, providing a reliable pathway for domain specialization in VLMs.