Update README.md

README.md

@@ -2,60 +2,128 @@
 
 ## 1. Overview
 
-The domain-specific recipe language model (RLM) is developed for an emerging scientific tool of robotic boxes, with perovskite solar cell research as a demonstration. For iterative fine-tuning of the RLM, seven artificial intelligence (AI) layers, including learning, generating, RecipeQA, fine-tuning, reasoning, evaluation, and optimisation, have been designed with a language agent. During the loops of seven AI layers, both numerical and semantic recipes are continuously learned and optimised for the RLM.
+Recipe Language Model (RLM): We introduce a domain-specific RLM developed through seven AI layers and interconnected robotic boxes to drive the evolution of physical AI in materials research.
 
 ---
 
 ## 2. Introduction
 
-Materials innovation have been undergoing rapid development with the vast combinatorial exploration of recipes; however, the related research suffers from time-consuming trial-and-error synthesis and labour-intensive fabrication. As a promising alternative, robotics enables high-throughput experimentation and data collection; however, the resulting numerical datasets are often insufficiently analysed and fail to provide effective feedback for semantic recipe optimisation.
+Materials innovation have been undergoing rapid development with the vast combinatorial exploration of recipes; however, the related research suffers from time-consuming trial-and-error synthesis and labour-intensive fabrication.
 
-Here, we present a domain-specific recipe language model (RLM) developed for an emerging scientific tool of robotic boxes (perovskite solar cell research as a demonstration). For iterative fine-tuning of the RLM, seven artificial intelligence (AI) layers, including learning, generating, RecipeQA, fine-tuning, reasoning, evaluation, and optimisation, have been designed with a language agent. During the loops of seven AI layers, both numerical and semantic recipes were continuously learned and optimised for the RLM. Guided by this RLM, eleven robotic boxes executed the controllable synthesis, fabrication and characterisation of 50,764 samples. Simultaneously, more than 578 million tokens were generated and augmented to improve the ability to recommend a recipe and mechanistic reasoning, reaching a level comparable to that of an experienced researcher.
+As a promising alternative, robotics enables high-throughput experimentation and data collection; however, the resulting numerical datasets are often insufficiently analysed and fail to provide effective feedback for semantic recipe optimisation.
+
+Here, we present a domain-specific recipe language model (RLM) developed for an emerging scientific tool of robotic boxes (perovskite solar cell research as a demonstration).
+
+For iterative fine-tuning of the RLM, seven artificial intelligence (AI) layers, including learning, generating, RecipeQA, fine-tuning, reasoning, evaluation, and optimisation, have been designed with a language agent.
+
+During the loops of seven AI layers, both numerical and semantic recipes were continuously learned and optimised for the RLM.
+
+Guided by this RLM, eleven robotic boxes executed the controllable synthesis, fabrication and characterisation of 50,764 samples.
+
+Simultaneously, more than 578 million tokens were generated and augmented to improve the ability to recommend a recipe and mechanistic reasoning, reaching a level comparable to that of an experienced researcher.
 
 Therefore, the integration of the RLM with robotic boxes enables an AI and robotics discovery process in which specialised language modelling and modularised robotic hardware continuously improve one another, suggesting an evolution of physical AI for materials research.
-Here, we present a domain-specific recipe language model (RLM) developed for an emerging scientific tool of robotic boxes, with perovskite solar cell research as a demonstration. For iterative fine-tuning of the RLM, seven artificial intelligence (AI) layers, including learning, generating, RecipeQA, fine-tuning, reasoning, evaluation, and optimisation, have been designed with a language agent. During the loops of seven AI layers, both numerical and semantic recipes are continuously learned and optimised for the RLM.
+
+Here, we present a domain-specific recipe language model (RLM) developed for an emerging scientific tool of robotic boxes, with perovskite solar cell research as a demonstration.
+
+For iterative fine-tuning of the RLM, seven artificial intelligence (AI) layers, including learning, generating, RecipeQA, fine-tuning, reasoning, evaluation, and optimisation, have been designed with a language agent.
+
+During the loops of seven AI layers, both numerical and semantic recipes are continuously learned and optimised for the RLM.
 
 ---
 
 ## 3. Model Description
 
-To train this domain-specific RLM, the workflow starts from encoded formulas and parameters as recipe inputs, proceeds through seven AI layers with the language agent, and produces in situ characterisation and device performance assessment as mechanistic outputs. The language agent encodes these machine-readable recipes into structured formulas and parameters sequences, which are translated into tokens for subsequent fine-tuning of the RLM and execution by the robotic boxes. As a result, the fine-tuned RLM incorporates the encoded recipes, robotics, and characterised results to form a closed recommendation–synthesis–fabrication–characterisation–mechanism loop for exploring the large space of the recipes and their underlying mechanisms.
+To train this domain-specific RLM, the workflow starts from encoded formulas and parameters as recipe inputs, proceeds through seven AI layers with the language agent, and produces in situ characterisation and device performance assessment as mechanistic outputs.
+
+The language agent encodes these machine-readable recipes into structured formulas and parameters sequences, which are translated into tokens for subsequent fine-tuning of the RLM and execution by the robotic boxes.
+
+As a result, the fine-tuned RLM incorporates the encoded recipes, robotics, and characterised results to form a closed recommendation–synthesis–fabrication–characterisation–mechanism loop for exploring the large space of the recipes and their underlying mechanisms.
 
 ---
 
 ## 4. Key Features
 
-Recipe recommendation: the ability to generate recommended recipes with recipe integrity, formula rationality, parameter rationality, and experimental validity.
+Acceleration of Materials Intelligence (MI): Simultaneously optimizes recipe recommendation (technical accuracy) and mechanistic reasoning (scientific understanding).
 
-Mechanistic reasoning: the ability to provide mechanistic explanations with domain knowledge, mechanism integrity, interpretation, comprehensiveness, and coherence.
+Evolution of Physical AI (PAI): Creates a synergy where the RLM enhances the robotic controllable fabrication, while the robotic outcomes continuously refine the RLM’s recipe and mechanism.
 
 ---
 
 ## 5. Training Details
 
-The model is trained using a multi-stage pipeline:
+Seven AI layers Architecture has been designed for this RLM Training.
+
+---
+
+### Learning
 
-- Data sources:
-  - Scientific literature
-  - Robotic experimental datasets
-  - Generated RecipeQA 
-- Training strategy:
-  - Supervised fine-tuning (SFT with LoRA)
-  - Direct preference optimisation (DPO) 
-- Data format:
-  - RecipeQA without mechanism
-  - RecipeQA with mechanism (Chain-of-Thought) 
+In the learning layer, the formulas and parameters are encoded and then tokenised into recipes as inputs.
+
+Through atomic skills of data extraction, cleaning, and matching, these data are organised into standardised datasets, providing the basis for RLM training and iterative recipe refinement.
 
 ---
 
-## 6. Intended Use
+### Generating
+
+In the generating layer, the tokenised recipes are comprised into the recipe report with fabrication details, mechanistic descriptions, an optimisation summary, and supporting information.
+
+Through atomic skills of edge reporting (generation from single experimental data), single-variable reporting (generation from matched data with single variable), and characterization reporting (generation from matched data with in situ characterization), these processed data are converted into robotic recipe reports.
+
+---
+
+### RecipeQA
+
+In the RecipeQA layer, the recipe reports are further converted into semantically structured question–answer pairs (RecipeQA).
+
+The primary objective of this layer is to construct high-quality, domain-specific training corpora through key atomic skills of Report to QA (convert recipe reports into semantically structured RecipeQA) and Distillation (knowledge distillation for RecipeQA).
+
+---
+
+### Fine-tuning
 
-RLM is designed to assist researchers, scientists, and industry professionals in recipe-driven domains that involve the vast combinatorial exploration of recipes and are often constrained by time-consuming trial-and-error synthesis and labour-intensive fabrication. 
+In the fine-tuning layer, the base model (Qwen3-32B) together with the RecipeQA corpora are taken as the input of this layer.
 
-Representative application scenarios include: 
-- Biomedicine 
-- Synthetic Biology
-- New-Energy Batteries
-- Semiconductor Materials
+Through low-rank adaptation (LoRA), the model is efficiently adapted to domain-specific recipe knowledge and transformed into a domain-specific RLM as output.
 
 ---
+
+### Reasoning
+
+In the reasoning layer, the fine-tuned domain-specific RLM to generate mechanistic interpretations, performance explanations, and recipe optimization suggestions from experimental records.
+
+These reasoning results serve as an important bridge between trained model capability and practical scientific decision-making, and also provide candidate knowledge and reasoning evidence for the downstream Evaluation Layer and Optimization Layer.
+
+---
+
+### Evaluation
+
+In the evaluation layer, the recipe recommendations and mechanistic reasoning are evaluated, in order to measure their effectiveness, reliability, and scientific validity.
+
+Through key atomic skills of recipe recommendation and mechanistic reasoning, the aspects of recipe integrity, formula rationality, parameter rationality, experimental validation, domain knowledge, mechanism integrity, interpretation, comprehensiveness and coherence are systematically assessed.
+
+---
+
+### Optimization
+
+In the optimization layer, the RLM to be optimised and preference pairs of positive and negative samples are taken as the input of this layer.
+
+Through atomic skill of Direct Preference Optimisation (DPO), an optimised RLM is obtained as output.
+
+This layer further aligns the model towards preference-consistent and high-performance recipe recommendation.
+
+---
+
+## 6. Intended Use
+
+The RLM is designed as a domain-specific framework to bridge the gap between abstract scientific knowledge and physical experimentation in materials research (herein perovskite solar cell research as a demonstration).
+
+By integrating seven AI layers and interconnected robotic systems, its intended use is to automate and evolve physical AI through the following potential applications:
+
+Autonomous Experimental Planning: The RLM translates high-level research objectives into granular, robot-executable "recipes". It functions as a high-level planner that identifies necessary actions, objects, and sequences required for materials synthesis and fabrication.
+
+Physical-AI Coevolution: It drives the "coevolution" of Large Language Models (LLMs) with physical models, refining the AI's ability to conduct domain-specific simulations while generating real-world data to steer broader intelligence.
+
+Knowledge-to-Action Translation: The model leverages its seven AI layers architecture to transform textual knowledge from scientific literature into structured, actionable steps, overcoming the "erudite scholar" limitation where AI possess knowledge but lacks the capacity for physical interaction.
+
+Self-Driving Labs Integration: It serves as the cognitive core for robotic boxes (embodied AI), enabling robots to interpret natural language prompts, reason over mechanistic context, and execute multi-step tasks like material characterization and performance verification.