LLM+P lets LLMs solve planning problems optimally by converting them to PDDL for classical planners and back to natural language.
arXiv preprint arXiv:2301.13379 , year=
7 Pith papers cite this work, alongside 23 external citations. Polarity classification is still indexing.
7
Pith papers citing it
23
external citations · external index
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
NeuroState-Bench supplies human-calibrated tasks and probes that measure commitment integrity in LLM agents and shows this measure diverges from ordinary task success.
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.
LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.
LLMs generated 615 vulnerable code snippets aligned with CAPEC and CWE frameworks across three languages, with 0.98 cosine similarity between model outputs.
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.
citing papers explorer
-
LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
LLM+P lets LLMs solve planning problems optimally by converting them to PDDL for classical planners and back to natural language.
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
-
NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles
NeuroState-Bench supplies human-calibrated tasks and probes that measure commitment integrity in LLM agents and shows this measure diverges from ordinary task success.
-
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.
-
LLM Reasoning Is Latent, Not the Chain of Thought
LLM reasoning is primarily mediated by latent-state trajectories rather than by explicit surface chain-of-thought outputs.
-
From Theory to Practice: Code Generation Using LLMs for CAPEC and CWE Frameworks
LLMs generated 615 vulnerable code snippets aligned with CAPEC and CWE frameworks across three languages, with 0.98 cosine similarity between model outputs.
-
The Rise and Potential of Large Language Model Based Agents: A Survey
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.