AI Agents Paper

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language...

Harnessing the power of human-annotated data through Supervised Fine-Tuning (SFT) is pivotal for adv...

Added ago

Self-Rewarding Language Models

We posit that to achieve superhuman agents, future models require superhuman feedback in order to pr...

Added ago

Direct Preference Optimization: Your Language Model is Secretly a Rewa...

While large-scale unsupervised language models (LMs) learn broad world knowledge and some reasoning ...

Added ago

GAIA-1: A Generative World Model for Autonomous Driving

Autonomous driving promises transformative improvements to transportation, but building systems capa...

Added ago

StreamDiffusion: A Pipeline-level Solution for Real-time Interactive G...

We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generati...

Added ago

Collective Intelligence for Deep Learning: A Survey of Recent Developm...

In the past decade, we have witnessed the rise of deep learning to dominate the field of artificial ...

Added ago

[DPO] Direct Preference Optimization: Your Language Model is Secretly ...

While large-scale unsupervised language models (LMs) learn broad world knowledge and some reasoning ...

Added ago

[AI Avalon] Finding Friend and Foe in Multi-Agent Games

Recent breakthroughs in AI for multi-agent games like Go, Poker, and Dota, have seen great strides i...

Added ago

AppAgent: Multimodal Agents as Smartphone Users

Recent advancements in large language models (LLMs) have led to the creation of intelligent agents c...

Added ago

GitHub - facebookresearch/diplomacy_cicero: Code for Cicero, an AI age...

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language nego...

Added ago

[AI Werewolf] Language Agents with Reinforcement Learning for Strategi...

Agents built with large language models (LLMs) have recently achieved great advancements.

Added ago

Building Cooperative Embodied Agents Modularly with Large Language Mod...

Large Language Models (LLMs) have demonstrated impressive planning abilities in single-agent embodie...

Added ago

WebArena: A Realistic Web Environment for Building Autonomous Agents

With advances in generative AI, there is now potential for autonomous agents to manage daily tasks v...

Added ago

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversati...

AutoGen is an open-source framework that allows developers to build LLM applications via multiple ag...

Added ago

Unleashing Cognitive Synergy in Large Language Models: A Task-Solving ...

Human intelligence thrives on the concept of cognitive synergy, where collaboration and information ...

Added ago

ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Deba...

Text evaluation has historically posed significant challenges, often demanding substantial labor and...

Added ago

ParlAI/parlai/tasks/light_multiparty at main · facebookresearch/ParlAI

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

Added ago

Multi-Party Chat: Conversational Agents in Group Settings with Humans ...

Current dialogue research primarily studies pairwise (two-party) conversations, and does not address...

Added ago

GitHub - sotopia-lab/sotopia

An environment that simulates and evaluates open-ended social interactions between AI and human agen...

Added ago

AgentVerse: Facilitating Multi-Agent Collaboration and Exploring...

Autonomous agents empowered by Large Language Models (LLMs) have undergone significant improvements,...

Added ago

Reflexion: Language Agents with Verbal Reinforcement Learning

Large language models (LLMs) have been increasingly used to interact with external environments (e.g...

Added ago

Teaching Large Language Models to Self-Debug

generate code based on question, execute the code and receive feedback.

Added ago

AgentTuning: Enabling Generalized Agent Abilities for LLMs

Enhance the agent abilities of LLMs while maintaining their general LLM capabilities with fintuning ...

Added ago

Lyfe Agents: generative agents for low-cost real-time social...

Highly autonomous generative agents powered by large language models promise to simulate intricate s...

Added ago