Notes / tag / planning-and-reasoning-algorithms

#planning-and-reasoning-algorithms

11 notes

1. Chain of Thought

Covers Chain-of-Thought prompting -- eliciting intermediate reasoning steps before a final answer -- why it improves multi-step task performance, and its limits on tasks requiring backtracking or exploration.

agentic-ai-engineering planning-and-reasoning-algorithms book

2. ReAct

Covers the ReAct pattern -- interleaving reasoning traces with tool-invoking actions in a single loop -- and why it became the default architecture for tool-using agents over pure chain-of-thought or plan-then-execute approaches.

agentic-ai-engineering planning-and-reasoning-algorithms book

3. Self-Consistency

Covers self-consistency decoding -- sampling multiple independent reasoning paths and taking a majority vote over final answers -- as a test-time technique for improving reliability without additional training.

agentic-ai-engineering planning-and-reasoning-algorithms book

4. Tree of Thoughts

Covers Tree-of-Thoughts search -- exploring multiple reasoning branches with lookahead and backtracking -- and when the added inference cost is justified over a single linear chain-of-thought pass.

agentic-ai-engineering planning-and-reasoning-algorithms book

5. Graph of Thoughts

Covers Graph-of-Thoughts reasoning, where intermediate thoughts can merge, refine, and feed back into each other as a DAG rather than a tree, and the problem classes where this generalization pays off over Tree-of-Thoughts.

agentic-ai-engineering planning-and-reasoning-algorithms book

6. Reflexion

Covers the Reflexion pattern -- an agent critiquing its own failed attempt in natural language and feeding that self-reflection back into the next attempt -- as a lightweight alternative to gradient-based learning from mistakes.

agentic-ai-engineering planning-and-reasoning-algorithms book

7. Plan-and-Execute

Covers Plan-and-Execute as a reasoning strategy -- front-loading a full plan in one reasoning pass before any tool result exists, versus ReAct's step-by-step interleaving of reasoning and observation -- and the stale-plan failure mode that ordering creates.

agentic-ai-engineering planning-and-reasoning-algorithms book

8. Program-Aided Language Models

Covers Program-Aided Language Models (PAL) -- offloading deterministic computation to generated code executed by an interpreter instead of having the LLM compute the answer directly -- and why this eliminates a specific class of arithmetic and logic errors.

agentic-ai-engineering planning-and-reasoning-algorithms book

9. LLM Compiler

Covers the LLM Compiler pattern -- planning a DAG of tool calls upfront and executing independent branches in parallel -- and the latency and cost wins over sequential ReAct-style execution for tasks with parallelizable sub-steps.

agentic-ai-engineering planning-and-reasoning-algorithms book

10. Debate & Critic Agents

Covers multi-agent debate and critic architectures, where separate agent roles argue opposing positions or critique a proposer's output, and the evidence for when this improves answer quality over single-agent self-reflection.

agentic-ai-engineering planning-and-reasoning-algorithms book

11. Hierarchical Planning

Covers hierarchical planning -- decomposing a goal into subgoals handled by higher- and lower-level planners at different abstraction levels -- and how this scales agent reasoning to long-horizon tasks that flat planning approaches struggle with.

agentic-ai-engineering planning-and-reasoning-algorithms book