diff --git a/diagrams/SIA_Component_Model.puml b/diagrams/SIA_Component_Model.puml
index 3a82693..5c7cc32 100644
--- a/diagrams/SIA_Component_Model.puml
+++ b/diagrams/SIA_Component_Model.puml
@@ -4,7 +4,7 @@ skinparam componentStyle uml2
package "SIA System" {
[LLM Engine] as LLM
- [Action System] as AS
+ [Agent Core] as AC
[Context Template] as CT
package "Modules" {
@@ -23,11 +23,11 @@ database "File System" as FS {
database "Git Repository" as GR
}
-AS -> LLM : Context
-LLM -> AS : Reasoning and actions
+AC -> LLM : Context
+LLM -> AC : Reasoning and actions
-CT --> AS : Context
-AS --> Modules : Commands to execute
+CT --> AC : Context
+AC --> Modules : Commands to execute
Modules --> CT : Data
DM -> DE : Container management
diff --git a/diagrams/SIA_Component_Model.svg b/diagrams/SIA_Component_Model.svg
index e5ad541..4cbdc51 100644
--- a/diagrams/SIA_Component_Model.svg
+++ b/diagrams/SIA_Component_Model.svg
@@ -1 +1 @@
-
\ No newline at end of file
+
\ No newline at end of file
diff --git a/readme.md b/readme.md
index bf1cacd..ec9f20a 100644
--- a/readme.md
+++ b/readme.md
@@ -38,13 +38,13 @@ The main context is always regenerated and contains:
- The reasoning, actions and results of the previous iteration
- Files monitored from the filesystem
-### Core Action System
+### Core Actions
Core actions are selected by the LLM by outputting an XML list of actions and parameters.
This system allows the agent to manage its memory, control containers, select wich version to run, and communicate.
-The Action System parses the XML output and executes the corresponding functions.
+The Agent Core parses the XML output and executes the corresponding functions.
-Core commands for user interaction:
+Core actions for user interaction:
- Read standard input
- Write to standard output
@@ -58,7 +58,7 @@ The short-lived containers define a timeout.
The next iteration of the main loop starts when the container finishes or the timeout is reached.
The long-lived containers can also be waited on at a later point in time.
-Core commands for container operations:
+Core actions for container operations:
- Start container
- Stop container
- Write to container standard input
@@ -75,7 +75,7 @@ Files and directories in this filesystem can be mapped as volumes to containers.
The agent can load a file in its context, so it always has a view of the latest version.
The same can be done with directory listings.
-Core commands for file operations:
+Core actions for file operations:
- Monitor file (or folder)
- Unmonitor file
@@ -91,7 +91,7 @@ The agent can access this by running a SIA container.
It can then test the updated LLM in another SIA instance in a container.
If it is acceptable it can change to this new version.
-Core commands for reinforcement learning:
+Core actions for reinforcement learning:
- Select LLM by file name
There are no specific commands for running a SIA instance in a container.
@@ -105,7 +105,7 @@ With these it is possible for SIA to update and test new versions of itself.
If a new version is approved, the agent can switch to it and continue working.
-Core commands for self-improvement:
+Core actions for self-improvement:
- Update to docker tag
## Architecture
@@ -130,14 +130,14 @@ Modules execute core commands and provide data for the main context.
- create dataset for fine-tuning the LLM
- labeling trained models
-### Action System
+### Agent Core
-The Action System runs the SIA main loop.
+The Agent Core runs the SIA main loop.
- request main context from the Context Manager
- run the LLM
- parse the LLM output
-- execute the appropriate commands on the relevant modules
+- execute the appropriate actions using the relevant modules
### Context Template
@@ -241,7 +241,7 @@ To use SIA several directories have to be mounted:
## Actions
-A list of all available core actions.
+A list of all available Core Actions.
Indicating how they are implemented and how SIA can use them.
### Read standard input