Increasing AI Intelligence

Reviews

• 2024-12: A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges

Prompt Engineering

• 2024-11: LLMs as Method Actors: A Model for Prompt Engineering and Architecture

Fine Tuning

• 2024-12: Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models

Proactive Search

Compute expended after training, but before inference.

Training Data (Data Refinement, Synthetic Data)

• C.f. image datasets:
  • 2023-06: StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners
  • 2023-11: DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback
• 2024-09: Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale
• 2024-10: Data Cleaning Using Large Language Models
• Updating list of links: Synthetic Data of LLMs, by LLMs, for LLMs

Generate consistent plans/thoughts

• 2024-08: Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers (code)
  • (Microsoft) rStar is a self-play mutual reasoning approach. A small model adds to MCTS using some defined reasoning heuristics. Mutually consistent trajectories can be emphasized.
• 2024-09: Self-Harmonized Chain of Thought
  • Produce refined chain-of-thought style solutions/prompts for diverse problems. Given a large set of problems/questions, first aggregated semantically, then apply zero-shot chain-of-thought to each problem. Then cross-pollinate between proposed solutions to similar problems, looking for refined and generalize solutions.
• 2024-11: LLMs Do Not Think Step-by-step In Implicit Reasoning
  • They argue that models trained to reproduce CoT outputs do not, internally, perform stepwise reasoning (with intermediate representations); this suggests that explicit CoT could be superior to implicit CoT.

Sampling

• 2024-11: Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding (code)

Automated prompt generation

• 2024-09: Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts

Distill inference-time-compute into model

• 2023-10: Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning (U. Maryland, Adobe)
• 2023-11: Implicit Chain of Thought Reasoning via Knowledge Distillation (Harvard, Microsoft, Hopkins)
• 2024-02: Grandmaster-Level Chess Without Search (Google DeepMind)
• 2024-07: Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models
• 2024-07: Distilling System 2 into System 1
• 2024-07: BOND: Aligning LLMs with Best-of-N Distillation
• 2024-09: Training Language Models to Self-Correct via Reinforcement Learning (Google DeepMind)
• 2024-10: Thinking LLMs: General Instruction Following with Thought Generation
• 2024-10: Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
• 2024-12: Training Large Language Models to Reason in a Continuous Latent Space

CoT reasoning model

• 2024-09: OpenAI o1
• 2024-10: O1 Replication Journey: A Strategic Progress Report – Part 1 (code): Attempt by Walnut Plan to reproduce o1-like in-context reasoning
• 2024-11: DeepSeek-R1-Lite-Preview reasoning model
• 2024-11: Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
• 2024-11: O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?
• 2024-12: o1-Coder: an o1 Replication for Coding (code)
• 2024-12: Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
• 2024-12: Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective

Scaling

• 2024-08: Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling (Google DeepMind)
• 2024-11: Scaling Laws for Pre-training Agents and World Models

Inference Time Compute

Methods

• 2024-03: Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
• 2024-11: Reverse Thinking Makes LLMs Stronger Reasoners
• 2024-12: Training Large Language Models to Reason in a Continuous Latent Space (Chain of Continuous Thought, COCONUT)

Review

• 2024-06: From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models

In context learning (ICL), search, and other inference-time methods

• 2023-03: Reflexion: Language Agents with Verbal Reinforcement Learning
• 2023-05: VOYAGER: An Open-Ended Embodied Agent with Large Language Models
• 2024-04: Many-Shot In-Context Learning
• 2024-08: Automated Design of Agentic Systems
• 2024-09: Planning In Natural Language Improves LLM Search For Code Generation

Inference-time Sampling

• 2024-10: entropix: Entropy Based Sampling and Parallel CoT Decoding
• 2024-10: TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
• 2024-11: Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs
• 2024-12: Guidance is All You Need: Temperature-Guided Reasoning in Large Language Models

Inference-time Gradient

• 2024-11: The Surprising Effectiveness of Test-Time Training for Abstract Reasoning (code)

Self-prompting

• 2023-05: Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling
• 2023-11: Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves

Retrieval or Memory

• 2024-12: Meta-Reflection: A Feedback-Free Reflection Learning Framework

In-context thought

• 2022-01: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (Google Brain)
• 2023-05: Tree of Thoughts: Deliberate Problem Solving with Large Language Models (Google DeepMind)
• 2024-05: Faithful Logical Reasoning via Symbolic Chain-of-Thought
• 2024-06: A Tree-of-Thoughts to Broaden Multi-step Reasoning across Languages
• 2024-09: To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
• 2024-09: Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning (Agnostiq, Toronto)
• 2024-09: Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models
• 2024-10: A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration (failed reasoning traces can improve CoT)
• 2024-10: Tree of Problems: Improving structured problem solving with compositionality
• 2023-01/2024-10: A Survey on In-context Learning

Naive multi-LLM (verification, majority voting, best-of-N, etc.)

• 2023-06: LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion (code)
• 2023-12: Dynamic Voting for Efficient Reasoning in Large Language Models
• 2024-04: Regularized Best-of-N Sampling to Mitigate Reward Hacking for Language Model Alignment
• 2024-08: Dynamic Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling
• 2024-11: Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models
• 2024-12: llm-consortium: Multiple LLMs collaboratively solve problems through structured dialogue, evaluation and arbitration

Multi-LLM (multiple comparisons, branching, etc.)

• 2024-10: Thinking LLMs: General Instruction Following with Thought Generation
• 2024-11: Mixtures of In-Context Learners: Multiple "experts", each with a different set of in-context examples; combine outputs at the level of next-token-prediction
• 2024-11: LLaVA-o1: Let Vision Language Models Reason Step-by-Step (code)

Iteration (e.g. neural-like layered blocks)

• 2024-06: Mixture-of-Agents Enhances Large Language Model Capabilities

Iterative reasoning via graphs

• 2023-08: Graph of Thoughts: Solving Elaborate Problems with Large Language Models
• 2023-10: Amortizing intractable inference in large language models (code)
• 2024-09: On the Diagram of Thought: Iterative reasoning as a directed acyclic graph (DAG)

Monte Carlo Tree Search (MCTS)

• 2024-05: AlphaMath Almost Zero: process Supervision without process
• 2024-06: ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
• 2024-06: Improve Mathematical Reasoning in Language Models by Automated Process Supervision
• 2024-06: Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B
• 2024-07: Tree Search for Language Model Agents
• 2024-10: Interpretable Contrastive Monte Carlo Tree Search Reasoning
• 2024-12: Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

Other Search

• 2024-11: Scattered Forest Search: Smarter Code Space Exploration with LLMs

Chain-of-Thought Reasoning

• 2017-05: Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems
• 2021-11: Training Verifiers to Solve Math Word Problems
• 2024-02: Chain-of-Thought Reasoning Without Prompting

Analysis

Scaling

• 2021-04: Scaling Scaling Laws with Board Games
• 2024-03: Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems
• 2024-04: The Larger the Better? Improved LLM Code-Generation via Budget Reallocation
• 2024-07: Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
• 2024-08: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
• 2024-08: Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• 2024-10: (comparing fine-tuning to in-context learning) Is In-Context Learning Sufficient for Instruction Following in LLMs?
• 2024-11: Inference Scaling FLaws: The Limits of LLM Resampling with Imperfect Verifiers

Theory

• 2024-02: Chain of Thought Empowers Transformers to Solve Inherently Serial Problems

Expending compute works

• 2024-06-10: Blog post (opinion): AI Search: The Bitter-er Lesson
• 2024-07-17: Blog post (test): Getting 50% (SoTA) on ARC-AGI with GPT-4o
• 2024-09-12: OpenAI o1: Learning to Reason with LLMs

• 2024-09-16: Scaling: The State of Play in AI

Pitfalls

• 2024-12: Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Pragmatics

Code for Inference-time Compute

• optillm: Inference proxy which implements state-of-the-art techniques to improve accuracy and performance of LLMs (improve reasoning over coding, logical and mathematical queries)

Memory

• 2024-10: Retriever-and-Memory: Towards Adaptive Note-Enhanced Retrieval-Augmented Generation

Tool Use

• 2024-11: DynaSaur: Large Language Agents Beyond Predefined Actions: writes functions/code to increase capabilities

Multi-agent Effort (and Emergent Intelligence)

• 2024-10: Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
• 2024-10: Agent-as-a-Judge: Evaluate Agents with Agents
• 2024-10: Two are better than one: Context window extension with multi-grained self-injection
• 2024-11: Project Sid: Many-agent simulations toward AI civilization

ML-like Optimization of LLM Setup

• 2023-03: DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines (code: Programming—not prompting—Foundation Models)
• 2024-05: Automatic Prompt Optimization with "Gradient Descent" and Beam Search
• 2024-06: TextGrad: Automatic "Differentiation" via Text (gradient backpropagation through text)
• 2024-06: Symbolic Learning Enables Self-Evolving Agents (optimize LLM frameworks)