Research — LLM Agents.md
Source Overview
A set of personal research notes exploring the practical mechanics of LLM agents — what patterns work beyond a single prompt, and where they tend to break. Research — LLM Agents.md
Central Question
*What actually makes an LLM "agent" work in practice, beyond a single prompt?*
The notes are organised around four sub-topics: the ReAct pattern, tool use, memory, and the planner-vs-reactive debate.
Sections at a Glance
| Section | Core claim | Notable flag |
|---|---|---|
| ReAct | Interleaves reasoning with tool calls; grounding beats pure chain-of-thought | Can loop / repeat failing actions |
| Tool use | Functions extend the model beyond training; schema structure reduces errors | Too many tools hurt selection accuracy |
| Memory | Short-term = context window; long-term = retrieval (RAG) | Contradiction flagged (see below) |
| Planning vs reactive | Planners = predictable but brittle; reactive = adaptive but may wander | Open question on when to prefer each |
Flagged Contradiction
The notes explicitly mark a disagreement on memory approaches:
- One note claims most "agent memory" is just retrieval + summarisation, and that naive vector search misses temporal and structural relationships.
- A cited paper claims embeddings alone suffice.
These positions conflict and are unresolved. Research — LLM Agents.md
Key Entities & Concepts Mentioned
- ReAct — reason-then-act loop pattern
- Chain-of-thought — baseline reasoning approach ReAct improves upon
- Tool use / function calling — search, code execution, external APIs
- Structured/forced tool schemas — proposed fix for tool-selection errors
- RAG (Retrieval-Augmented Generation) — primary mechanism for long-term memory
- Vector search / embeddings — memory retrieval mechanism (disputed sufficiency)
- Explicit planners — decompose-then-execute agent architecture
- Reactive loops — ReAct-style adaptive execution
What This Source Contributes
This source provides a framing scaffold for the research wiki: it names the four main sub-topics, surfaces a concrete contradiction worth investigating (embeddings vs richer memory), and poses the open planning question as an explicit research gap. It does not itself resolve any of these questions — resolution (if any) must come from the underlying articles and papers referenced in the notes.