Branch-Solve-Merge Improves Large Language Model Evaluation and Generation
Paper
•
2310.15123
•
Published
•
7
Agent
-
-
ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
Paper • 2310.13227 • Published • 12 -
LASER: LLM Agent with State-Space Exploration for Web Navigation
Paper • 2309.08172 • Published • 11 -
Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
Paper • 2310.04406 • Published • 8 -
Autonomous Tree-search Ability of Large Language Models
Paper • 2310.10686 • Published • 2 -
Tree-Planner: Efficient Close-loop Task Planning with Large Language Models
Paper • 2310.08582 • Published • 2 -
Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning
Paper • 2310.04474 • Published • 2 -
AgentTuning: Enabling Generalized Agent Abilities for LLMs
Paper • 2310.12823 • Published • 35 -
FireAct: Toward Language Agent Fine-tuning
Paper • 2310.05915 • Published • 2 -
Adapting LLM Agents Through Communication
Paper • 2310.01444 • Published • 3 -
MusicAgent: An AI Agent for Music Understanding and Generation with Large Language Models
Paper • 2310.11954 • Published • 24 -
Promptor: A Conversational and Autonomous Prompt Generation Agent for Intelligent Text Entry Techniques
Paper • 2310.08101 • Published • 2 -
SAI: Solving AI Tasks with Systematic Artificial Intelligence in Communication Network
Paper • 2310.09049 • Published • 1 -
SmartPlay : A Benchmark for LLMs as Intelligent Agents
Paper • 2310.01557 • Published • 12 -
Are Human-generated Demonstrations Necessary for In-context Learning?
Paper • 2309.14681 • Published • 1 -
Agent Instructs Large Language Models to be General Zero-Shot Reasoners
Paper • 2310.03710 • Published • 2 -
Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration
Paper • 2310.00280 • Published • 3 -
SteP: Stacked LLM Policies for Web Actions
Paper • 2310.03720 • Published • 7 -
You Only Look at Screens: Multimodal Chain-of-Action Agents
Paper • 2309.11436 • Published • 1 -
MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
Paper • 2309.10691 • Published • 4 -
Lemur: Harmonizing Natural Language and Code for Language Agents
Paper • 2310.06830 • Published • 31 -
EcoAssistant: Using LLM Assistant More Affordably and Accurately
Paper • 2310.03046 • Published • 5 -
SALMON: Self-Alignment with Principle-Following Reward Models
Paper • 2310.05910 • Published • 2 -
SCREWS: A Modular Framework for Reasoning with Revisions
Paper • 2309.13075 • Published • 15 -
DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
Paper • 2310.03714 • Published • 30 -
LLM Guided Inductive Inference for Solving Compositional Problems
Paper • 2309.11688 • Published • 1 -
AskIt: Unified Programming Interface for Programming with Large Language Models
Paper • 2308.15645 • Published • 2 -
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
Paper • 2309.17452 • Published • 3 -
CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
Paper • 2310.08992 • Published • 10 -
A Zero-Shot Language Agent for Computer Control with Structured Reflection
Paper • 2310.08740 • Published • 14 -
CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization
Paper • 2310.10134 • Published • 1 -
Multimodal Multi-Hop Question Answering Through a Conversation Between Tools and Efficiently Finetuned Large Language Models
Paper • 2309.08922 • Published • 1 -
ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings
Paper • 2305.11554 • Published • 2 -
GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution
Paper • 2307.08775 • Published • 1 -
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
Paper • 2305.18323 • Published • 1 -
Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models
Paper • 2304.09842 • Published • 1 -
Visual Programming: Compositional visual reasoning without training
Paper • 2211.11559 • Published • 1 -
Agents: An Open-source Framework for Autonomous Language Agents
Paper • 2309.07870 • Published • 42 -
ControlLLM: Augment Language Models with Tools by Searching on Graphs
Paper • 2310.17796 • Published • 16 -
Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency
Paper • 2309.17382 • Published • 4 -
Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach
Paper • 2306.03604 • Published • 1 -
ComputeGPT: A computational chat model for numerical problems
Paper • 2305.06223 • Published • 1 -
Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning
Paper • 2309.10814 • Published • 3 -
Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
Paper • 2211.12588 • Published • 3 -
Structured Chain-of-Thought Prompting for Code Generation
Paper • 2305.06599 • Published • 1 -
Of Models and Tin Men: A Behavioural Economics Study of Principal-Agent Problems in AI Alignment using Large-Language Models
Paper • 2307.11137 • Published • 1 -
ExpeL: LLM Agents Are Experiential Learners
Paper • 2308.10144 • Published • 2 -
i-Code Studio: A Configurable and Composable Framework for Integrative AI
Paper • 2305.13738 • Published • 1 -
AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn
Paper • 2306.08640 • Published • 26 -
CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
Paper • 2309.17428 • Published • 1 -
ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
Paper • 2307.16789 • Published • 98 -
Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models
Paper • 2308.00675 • Published • 35 -
DocPrompting: Generating Code by Retrieving the Docs
Paper • 2207.05987 • Published • 1 -
Toolformer: Language Models Can Teach Themselves to Use Tools
Paper • 2302.04761 • Published • 11 -
GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction
Paper • 2305.18752 • Published • 3 -
ToolCoder: Teach Code Generation Models to use API search tools
Paper • 2305.04032 • Published • 1 -
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
Paper • 2308.10848 • Published • 1 -
Syntax Error-Free and Generalizable Tool Use for LLMs via Finite-State Decoding
Paper • 2310.07075 • Published • 1 -
A Survey on Large Language Model based Autonomous Agents
Paper • 2308.11432 • Published • 1 -
OpenAGI: When LLM Meets Domain Experts
Paper • 2304.04370 • Published • 1 -
Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents
Paper • 2306.03314 • Published • 2 -
Exploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt Engineering
Paper • 2308.07411 • Published • 2 -
Cognitive Architectures for Language Agents
Paper • 2309.02427 • Published • 8 -
The Rise and Potential of Large Language Model Based Agents: A Survey
Paper • 2309.07864 • Published • 7 -
Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning
Paper • 2309.01352 • Published • 1 -
Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration
Paper • 2307.05300 • Published • 18 -
Communicative Agents for Software Development
Paper • 2307.07924 • Published • 3 -
Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs
Paper • 2311.05657 • Published • 27 -
JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models
Paper • 2311.05997 • Published • 36 -
Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
Paper • 2310.02304 • Published • 1 -
Is AI the better programming partner? Human-Human Pair Programming vs. Human-AI pAIr Programming
Paper • 2306.05153 • Published • 1 -
"Teach AI How to Code": Using Large Language Models as Teachable Agents for Programming Education
Paper • 2309.14534 • Published • 2 -
Towards Teachable Conversational Agents
Paper • 2102.10387 • Published • 1 -
Dynamic Planning with a LLM
Paper • 2308.06391 • Published • 2 -
LLM Augmented Hierarchical Agents
Paper • 2311.05596 • Published • 1 -
Execution-Based Evaluation for Open-Domain Code Generation
Paper • 2212.10481 • Published • 1 -
ToolTalk: Evaluating Tool-Usage in a Conversational Setting
Paper • 2311.10775 • Published • 7 -
MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
Paper • 2310.03128 • Published • 1 -
TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems
Paper • 2311.11315 • Published • 6 -
Understanding HTML with Large Language Models
Paper • 2210.03945 • Published • 1 -
Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators
Paper • 2306.01242 • Published • 2 -
Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning
Paper • 2312.14878 • Published • 13 -
GAIA: a benchmark for General AI Assistants
Paper • 2311.12983 • Published • 184 -
Modeling Complex Mathematical Reasoning via Large Language Model based MathAgent
Paper • 2312.08926 • Published • 7 -
ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent
Paper • 2312.10003 • Published • 36 -
CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
Paper • 2401.03065 • Published • 11 -
AutoAgents: A Framework for Automatic Agent Generation
Paper • 2309.17288 • Published • 4 -
If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents
Paper • 2401.00812 • Published • 2 -
Pop Quiz! Do Pre-trained Code Models Possess Knowledge of Correct API Names?
Paper • 2309.07804 • Published • 2 -
Prompt2Model: Generating Deployable Models from Natural Language Instructions
Paper • 2308.12261 • Published • 1 -
EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction
Paper • 2401.06201 • Published • 2 -
LEVER: Learning to Verify Language-to-Code Generation with Execution
Paper • 2302.08468 • Published • 1 -
ProTIP: Progressive Tool Retrieval Improves Planning
Paper • 2312.10332 • Published • 7 -
TravelPlanner: A Benchmark for Real-World Planning with Language Agents
Paper • 2402.01622 • Published • 33 -
SymbolicAI: A framework for logic-based approaches combining generative models and solvers
Paper • 2402.00854 • Published • 19 -
Efficient Exploration for LLMs
Paper • 2402.00396 • Published • 21 -
Efficient Tool Use with Chain-of-Abstraction Reasoning
Paper • 2401.17464 • Published • 16 -
LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents
Paper • 2311.05437 • Published • 48 -
Empowering LLM to use Smartphone for Intelligent Task Automation
Paper • 2308.15272 • Published • 1 -
AgentScope: A Flexible yet Robust Multi-Agent Platform
Paper • 2402.14034 • Published • 12 -
Large Language Model based Multi-Agents: A Survey of Progress and Challenges
Paper • 2402.01680 • Published • 2 -
LLM Multi-Agent Systems: Challenges and Open Problems
Paper • 2402.03578 • Published -
Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies
Paper • 2402.03628 • Published -
S-Agents: self-organizing agents in open-ended environment
Paper • 2402.04578 • Published -
SpeechAgents: Human-Communication Simulation with Multi-Modal Multi-Agent Systems
Paper • 2401.03945 • Published -
LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error
Paper • 2403.04746 • Published • 22 -
LLM Agent Operating System
Paper • 2403.16971 • Published • 65 -
MuMath-Code: Combining Tool-Use Large Language Models with Multi-perspective Data Augmentation for Mathematical Reasoning
Paper • 2405.07551 • Published -
ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
Paper • 2401.00741 • Published -
AgileCoder: Dynamic Collaborative Agents for Software Development based on Agile Methodology
Paper • 2406.11912 • Published • 26 -
From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents
Paper • 2409.03512 • Published • 26 -
How to Build an AI Tutor that Can Adapt to Any Course and Provide Accurate Answers Using Large Language Model and Retrieval-Augmented Generation
Paper • 2311.17696 • Published