LLMs show up to 60.58% social bias in generated code; a new Fairness Monitor Agent cuts bias by 65.1% and raises functional correctness from 75.80% to 83.97%.
hub
Self-collaboration code generation via chatgpt
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
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.
ARM evolves specialized reasoning modules from basic CoT via tree search to serve as reusable components in multi-agent systems that generalize across models and domains without per-task re-optimization.
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.
Introduces NoisyToolBench benchmark and Ask-when-Needed framework to improve LLM tool-use performance when user instructions are unclear or incomplete.
DyLAN automatically selects and dynamically organizes LLM agents for collaboration, outperforming fixed-agent baselines on code generation, reasoning, and decision tasks with up to 25% accuracy gains on some MMLU subjects.
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.
AutoGen provides an open-source framework for multi-agent LLM conversations that support customizable interactions across diverse applications.
A-ProS uses a hybrid multi-model feedback framework with stateful refinement to improve success rates on competitive programming problems, achieving over 2x gains compared to baseline agent loops.
TransAgent improves LLM code translation by up to 33.3% via multi-agent fine-grained execution alignment on a new benchmark of recent tasks.
Proposes and tests a constitutive definition of 'agent harness' via conceptual analysis of literature and six real systems.
Iterative self-repair improves LLM code pass rates by 4.9-17.1 pp on HumanEval and 16-30 pp on MBPP across seven models, with gains concentrated early and syntax errors easier to fix than logical ones.
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.
-
Learning to Ask: When LLM Agents Meet Unclear Instruction
Introduces NoisyToolBench benchmark and Ask-when-Needed framework to improve LLM tool-use performance when user instructions are unclear or incomplete.
-
A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration
DyLAN automatically selects and dynamically organizes LLM agents for collaboration, outperforming fixed-agent baselines on code generation, reasoning, and decision tasks with up to 25% accuracy gains on some MMLU subjects.