RAP turns LLMs into dual world-model and planning agents via MCTS to generate better reasoning paths, outperforming CoT baselines and achieving 33% relative gains over GPT-4 CoT using LLaMA-33B on plan generation.
arXiv preprint arXiv:2110.07178 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Distilling step-by-step uses LLM-generated rationales as additional supervision in a multi-task framework so that 770M-parameter models outperform 540B-parameter models on NLP benchmarks with only 80% of the data.
AgentTrust v2 deploys an LLM judge with self-learning on semantic attacks to raise accuracy from 48% to 83.6-85.2% while distilling rules and using guarded RAG, cutting judge calls and eliminating benign blocks over 45k actions.
Larger LLMs reproduce constructional productivity via entrenchment in coercion cases with nonce words but fail to use statistical preemption to avoid overgeneralizing semantically plausible but unobserved patterns.
Overmind is a neuro-symbolic architecture that uses adjustable Padé approximations and memory bypass to deliver 8.1 TOPS/W efficiency and 410 GOPS throughput on mixed workloads with minimal accuracy loss.
citing papers explorer
-
Reasoning with Language Model is Planning with World Model
RAP turns LLMs into dual world-model and planning agents via MCTS to generate better reasoning paths, outperforming CoT baselines and achieving 33% relative gains over GPT-4 CoT using LLaMA-33B on plan generation.
-
Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes
Distilling step-by-step uses LLM-generated rationales as additional supervision in a multi-task framework so that 770M-parameter models outperform 540B-parameter models on NLP benchmarks with only 80% of the data.
-
AgentTrust: A Self-Improving Trust Layer for AI-Agent Actions
AgentTrust v2 deploys an LLM judge with self-learning on semantic attacks to raise accuracy from 48% to 83.6-85.2% while distilling rules and using guarded RAG, cutting judge calls and eliminating benign blocks over 45k actions.
-
Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt
Larger LLMs reproduce constructional productivity via entrenchment in coercion cases with nonce words but fail to use statistical preemption to avoid overgeneralizing semantically plausible but unobserved patterns.
-
Overmind NSA: A Unified Neuro-Symbolic Computing Architecture with Approximate Nonlinear Activations and Preemptive Memory Bypass
Overmind is a neuro-symbolic architecture that uses adjustable Padé approximations and memory bypass to deliver 8.1 TOPS/W efficiency and 410 GOPS throughput on mixed workloads with minimal accuracy loss.