Increasing AI Intelligence - Revision history

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

2026-01-22T15:44:58Z

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

2025-12-12T22:45:36Z

‎Analysis

2025-10-20T16:50:44Z

‎Inference-time Sampling

2025-10-19T23:04:33Z

‎Expending compute works

2025-10-17T16:42:18Z

‎Scaling

2025-10-17T16:42:08Z

‎Reinforcement Learning

2025-10-15T16:26:00Z

‎Interact with Environment

2025-10-02T18:23:10Z

‎Reinforcement Learning

2025-10-02T18:20:02Z

‎Interact with Environment

2025-09-24T13:19:02Z

‎Multi-agent Effort (and Emergent Intelligence)

@@ Line 195: / Line 195: @@
 * 2025-02: [https://arxiv.org/abs/2502.04506 When One LLM Drools, Multi-LLM Collaboration Rules]
 * 2025-03: [https://arxiv.org/abs/2503.17363 Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique]
 ===Multi-LLM (multiple comparisons, branching, etc.)===

@@ Line 272: / Line 272: @@
 * 2025-04: [https://arxiv.org/abs/2504.03635 Do Larger Language Models Imply Better Reasoning? A Pretraining Scaling Law for Reasoning]: Model size can improve things, but can also lead to overparametrization (memorization instead of reasoning)
 * 2025-04: [https://arxiv.org/abs/2504.14047 Think Deep, Think Fast: Investigating Efficiency of Verifier-free Inference-time-scaling Methods]: Reasoning models outperform inference-time-compute of non-reasoning; majority voting always helps, and is hard to beat
 ====(Optimal) Usage of Reasoning Compute====

@@ Line 158: / Line 158: @@
 * 2024-12: [https://arxiv.org/abs/2412.06822 Guidance is All You Need: Temperature-Guided Reasoning in Large Language Models]
 * 2025-08: [https://arxiv.org/abs/2508.15260 Deep Think with Confidence] ([https://jiaweizzhao.github.io/deepconf/ project])
 ===Inference-time Gradient/Updating/RL/etc.===

@@ Line 299: / Line 299: @@
 * 2024-09-16: [https://www.oneusefulthing.org/p/scaling-the-state-of-play-in-ai Scaling: The State of Play in AI]
 * 2025-02-03: [https://arxiv.org/abs/2502.06807 Competitive Programming with Large Reasoning Models]
 ==Pragmatics==

@@ Line 134: / Line 134: @@
 * 2025-02: [https://arxiv.org/pdf/2502.20339 Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners]
 * 2025-03: [https://arxiv.org/abs/2503.10061 Compute Optimal Scaling of Skills: Knowledge vs Reasoning]
 =Inference Time Compute=

@@ Line 43: / Line 43: @@
 * 2025-09: [https://www.nature.com/articles/s41586-025-09422-z DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning]
 * 2025-09: [https://github.com/NVlabs/RLP/blob/main/pdf/RLP_Reinforcement_as_a_Pretraining_Objective.pdf RLP : Reinforcement Learning Pre‑training] (Nvidia)
 ====Optimize Confidence/Entropy====

@@ Line 302: / Line 302: @@
 * [https://github.com/codelion/optillm 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=
+=Interact with Environment (Experiential Learning)=
 * 2025-01: [https://arxiv.org/abs/2501.10893 Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments]
 * 2025-09: [https://arxiv.org/abs/2509.24527 Training Agents Inside of Scalable World Models]
 =Memory=

@@ Line 323: / Line 323: @@
 * 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]
 ==Competition==