A three-agent loop of code generation, test creation, and execution feedback lifts pass@1 to 96.3% on HumanEval and 91.8% on MBPP for GPT-4 while using roughly half the tokens of prior state-of-the-art.
hub Canonical reference
Training socially aligned language models in simulated human society.arXiv preprint arXiv:2305.16960, 2023a
Canonical reference. 83% of citing Pith papers cite this work as background.
12
Pith papers citing it
Background
83% of classified citations
hub tools
citation-role summary
background 4
dataset 1
method 1
citation-polarity summary
representative citing papers
TeamTR is a trust-region framework for multi-agent LLM fine-tuning that resamples trajectories after each update to convert quadratic compounding occupancy shift into linear scaling and yields per-update improvement lower bounds.
AgentSociety is a large-scale LLM agent-based social simulator validated on polarization, UBI, disasters, and sustainability issues with alignment to real experiments.
CoALA is a modular cognitive architecture for language agents that organizes memory components, action spaces for internal and external interaction, and a generalized decision-making loop to support more systematic development of capable agents.
A survey of LLM-based autonomous agents that proposes a unified framework for their construction and reviews applications in social science, natural science, and engineering along with evaluation methods and future directions.
Multi-agent debate among LLMs yields more reliable text evaluations than single-agent prompting by simulating collaborative human judgment.
Transformer models trained on synthetic pedagogical interaction data in spatial navigation achieve more robust expert-like performance than those trained only on expert demonstrations, particularly when they can distinguish epistemic states of expert and novice agents.
TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt utility.
Survey organizes LLM trustworthiness into seven categories and 29 sub-categories, measures eight sub-categories on popular models, and finds that more aligned models generally score higher but with varying effectiveness.
The paper surveys the origins, frameworks, applications, and open challenges of AI agents built on large language models.
This survey reviews the background, key techniques, and evaluation methods for large language models, emphasizing emergent abilities that appear at large scales.
Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.
citing papers explorer
-
AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
A three-agent loop of code generation, test creation, and execution feedback lifts pass@1 to 96.3% on HumanEval and 91.8% on MBPP for GPT-4 while using roughly half the tokens of prior state-of-the-art.
-
TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination
TeamTR is a trust-region framework for multi-agent LLM fine-tuning that resamples trajectories after each update to convert quadratic compounding occupancy shift into linear scaling and yields per-update improvement lower bounds.
-
AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society
AgentSociety is a large-scale LLM agent-based social simulator validated on polarization, UBI, disasters, and sustainability issues with alignment to real experiments.
-
Cognitive Architectures for Language Agents
CoALA is a modular cognitive architecture for language agents that organizes memory components, action spaces for internal and external interaction, and a generalized decision-making loop to support more systematic development of capable agents.
-
A Survey on Large Language Model based Autonomous Agents
A survey of LLM-based autonomous agents that proposes a unified framework for their construction and reviews applications in social science, natural science, and engineering along with evaluation methods and future directions.
-
ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
Multi-agent debate among LLMs yields more reliable text evaluations than single-agent prompting by simulating collaborative human judgment.
-
Representing expertise accelerates learning from pedagogical interaction data
Transformer models trained on synthetic pedagogical interaction data in spatial navigation achieve more robust expert-like performance than those trained only on expert demonstrations, particularly when they can distinguish epistemic states of expert and novice agents.
-
TrustLLM: Trustworthiness in Large Language Models
TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt utility.
-
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Survey organizes LLM trustworthiness into seven categories and 29 sub-categories, measures eight sub-categories on popular models, and finds that more aligned models generally score higher but with varying effectiveness.
-
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.
-
A Survey of Large Language Models
This survey reviews the background, key techniques, and evaluation methods for large language models, emphasizing emergent abilities that appear at large scales.
-
Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.