Difference between revisions of "Increasing AI Intelligence"

From GISAXS
Jump to: navigation, search
(→‎Scaling)
(→‎ML-like Optimization of LLM Setup)
 
(15 intermediate revisions by the same user not shown)
Line 8: Line 8:
 
* 2025-03: [https://arxiv.org/abs/2503.24377 Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models]
 
* 2025-03: [https://arxiv.org/abs/2503.24377 Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models]
 
* 2025-04: [https://arxiv.org/abs/2504.09037 A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems]
 
* 2025-04: [https://arxiv.org/abs/2504.09037 A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems]
 +
* 2025-05: [https://lilianweng.github.io/posts/2025-05-01-thinking/ Why We Think]
 
* Links to papers: [https://github.com/hijkzzz/Awesome-LLM-Strawberry Awesome LLM Strawberry (OpenAI o1)]
 
* Links to papers: [https://github.com/hijkzzz/Awesome-LLM-Strawberry Awesome LLM Strawberry (OpenAI o1)]
  
Line 35: Line 36:
 
===Reinforcement Learning===
 
===Reinforcement Learning===
 
* 2025-04: DeepSeek: [https://arxiv.org/abs/2504.02495 Inference-Time Scaling for Generalist Reward Modeling]
 
* 2025-04: DeepSeek: [https://arxiv.org/abs/2504.02495 Inference-Time Scaling for Generalist Reward Modeling]
 +
* 2025-04: [https://arxiv.org/abs/2504.13837 Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?]
 
* 2025-04: [https://arxiv.org/abs/2504.13941 NEMOTRON-CROSSTHINK: Scaling Self-Learning beyond Math Reasoning]
 
* 2025-04: [https://arxiv.org/abs/2504.13941 NEMOTRON-CROSSTHINK: Scaling Self-Learning beyond Math Reasoning]
 +
* 2025-04: [https://arxiv.org/abs/2504.16084 TTRL: Test-Time Reinforcement Learning] ([https://github.com/PRIME-RL/TTRL code])
 +
* 2025-04: [https://arxiv.org/abs/2504.20571 Reinforcement Learning for Reasoning in Large Language Models with One Training Example]
 +
* 2025-05: [https://arxiv.org/abs/2505.03335 Absolute Zero: Reinforced Self-play Reasoning with Zero Data]
 +
 +
====Optimize Confidence/Entropy====
 +
* C.f. 2025-02: [https://arxiv.org/abs/2502.06233 Confidence Improves Self-Consistency in LLMs]
 +
* [https://x.com/xuandongzhao/status/1927270931874910259 2025-05]: [https://arxiv.org/abs/2505.19590 Learning to Reason without External Rewards] ([https://github.com/sunblaze-ucb/Intuitor code]): Reinforcement Learning from Internal Feedback, RLIF
 +
* [https://x.com/mihirp98/status/1927767453490172277 2025-05]: [https://rent-rl.github.io/ Maximizing Confidence Alone Improves Reasoning] ([https://github.com/satrams/rent-rl code]); a.k.a. RENT: Reinforcement Learning via Entropy Minimization.
 +
* 2025-05: [https://arxiv.org/abs/2505.22617 The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models]
 +
* 2025-06: [https://arxiv.org/abs/2506.01347 The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning]
  
 
====Exceed humans, using human-level data====
 
====Exceed humans, using human-level data====
Line 138: Line 150:
 
* 2024-12: [https://arxiv.org/abs/2412.06822 Guidance is All You Need: Temperature-Guided Reasoning in Large Language Models]
 
* 2024-12: [https://arxiv.org/abs/2412.06822 Guidance is All You Need: Temperature-Guided Reasoning in Large Language Models]
  
−
===Inference-time Gradient===
+
===Inference-time Gradient/Updating/RL/etc.===
 
* 2024-11: [https://ekinakyurek.github.io/papers/ttt.pdf The Surprising Effectiveness of Test-Time Training for Abstract Reasoning] ([https://github.com/ekinakyurek/marc code])
 
* 2024-11: [https://ekinakyurek.github.io/papers/ttt.pdf The Surprising Effectiveness of Test-Time Training for Abstract Reasoning] ([https://github.com/ekinakyurek/marc code])
 +
* 2025-04: [https://arxiv.org/abs/2504.16084 TTRL: Test-Time Reinforcement Learning] ([https://github.com/PRIME-RL/TTRL code])
  
 
===Self-prompting===
 
===Self-prompting===
Line 211: Line 224:
 
* 2025-03: [https://arxiv.org/abs/2503.19877 Scaling Evaluation-time Compute with Reasoning Models as Process Evaluators]
 
* 2025-03: [https://arxiv.org/abs/2503.19877 Scaling Evaluation-time Compute with Reasoning Models as Process Evaluators]
 
* 2025-03: [https://arxiv.org/abs/2503.23513 RARE: Retrieval-Augmented Reasoning Modeling]
 
* 2025-03: [https://arxiv.org/abs/2503.23513 RARE: Retrieval-Augmented Reasoning Modeling]
 +
 +
===Inner Monologue===
 +
* 2022-07: [https://arxiv.org/abs/2207.05608 Inner Monologue: Embodied Reasoning through Planning with Language Models]
 +
* 2025-06: [https://nicolehsing.com/mirror-paper.pdf MIRROR: Cognitive Inner Monologue Between Conversational Turns for Persistent Reflection and Reasoning in Conversational LLMs] ([https://github.com/nicolehsing/MIRROR code])
  
 
===Model Merging===
 
===Model Merging===
Line 246: Line 263:
 
* 2025-04: [https://arxiv.org/abs/2504.05185 Concise Reasoning via Reinforcement Learning]
 
* 2025-04: [https://arxiv.org/abs/2504.05185 Concise Reasoning via Reinforcement Learning]
 
* 2025-04: [https://arxiv.org/abs/2504.05419 Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification]
 
* 2025-04: [https://arxiv.org/abs/2504.05419 Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification]
 +
* 2025-04: [https://arxiv.org/abs/2504.15895 Dynamic Early Exit in Reasoning Models]
  
 
====Usage of Training Data====
 
====Usage of Training Data====
Line 287: Line 305:
 
* 2025-01: [https://arxiv.org/abs/2501.13946 Hallucination Mitigation using Agentic AI Natural Language-Based Frameworks]
 
* 2025-01: [https://arxiv.org/abs/2501.13946 Hallucination Mitigation using Agentic AI Natural Language-Based Frameworks]
 
* 2025-02: [https://arxiv.org/abs/2502.16111 PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving]
 
* 2025-02: [https://arxiv.org/abs/2502.16111 PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving]
 +
 +
==Competition==
 +
* 2025-06: [https://arxiv.org/abs/2506.04721 SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat]
  
 
=ML-like Optimization of LLM Setup=
 
=ML-like Optimization of LLM Setup=
Line 294: Line 315:
 
* 2024-06: [https://arxiv.org/abs/2406.18532 Symbolic Learning Enables Self-Evolving Agents] (optimize LLM frameworks)
 
* 2024-06: [https://arxiv.org/abs/2406.18532 Symbolic Learning Enables Self-Evolving Agents] (optimize LLM frameworks)
 
* 2025-03: [https://www.nature.com/articles/s41586-025-08661-4 Optimizing generative AI by backpropagating language model feedback]
 
* 2025-03: [https://www.nature.com/articles/s41586-025-08661-4 Optimizing generative AI by backpropagating language model feedback]
 +
 +
=Self-modification=
 +
* 2025-06: [https://arxiv.org/abs/2506.10943 Self-Adapting Language Models]
  
 
=Limitations/Requirements=
 
=Limitations/Requirements=

Latest revision as of 11:29, 14 June 2025

Contents

Reviews

World Model

Prompt Engineering

Thought Templates

Automatic Prompt Optimization

Fine Tuning

Proactive Search

Compute expended after training, but before inference.

Reinforcement Learning

Optimize Confidence/Entropy

Exceed humans, using human-level data

Training Data (Data Refinement, Synthetic Data)

Re-captioning

Pre-generate material

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

Automated prompt generation

Distill inference-time-compute into model

CoT reasoning model

See also: AI tools > LLM > Open-weights LLM > Reasoning

Scaling

Inference Time Compute

Methods

Review

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

Inference-time Sampling

Inference-time Gradient/Updating/RL/etc.

Self-prompting

Retrieval or Memory

In-context thought

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

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

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

Iterative reasoning via graphs

Monte Carlo Tree Search (MCTS)

Other Search

Chain-of-Thought Reasoning

Inner Monologue

Model Merging

Meta-methods

Analysis

Scaling

(Optimal) Usage of Reasoning Compute

Usage of Training Data

  • 2025-02: LIMO: Less is More for Reasoning (surprisingly easy generalization, from very few reasoning training examples; model can go from knowledge-retrieval to diverse reasoning using curated examples)

Theory

Expending compute works

Compute.png

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)

Interact with Environment

Memory

Tool Use

Integrated

Multi-agent Effort (and Emergent Intelligence)

Competition

ML-like Optimization of LLM Setup

Self-modification

Limitations/Requirements

Creativity

See: AI creativity

See Also

Retrieved from "http://gisaxs.com/index.php?title=Increasing_AI_Intelligence&oldid=7924"