Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
Paper • 2310.04406 • Published • 10
LM Prompt Engineering
-
-
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Paper • 2305.10601 • Published • 15 -
Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models
Paper • 2404.02575 • Published • 50 -
Voyager: An Open-Ended Embodied Agent with Large Language Models
Paper • 2305.16291 • Published • 13 -
LASER: LLM Agent with State-Space Exploration for Web Navigation
Paper • 2309.08172 • Published • 14 -
Reflexion: Language Agents with Verbal Reinforcement Learning
Paper • 2303.11366 • Published • 6 -
ReAct: Synergizing Reasoning and Acting in Language Models
Paper • 2210.03629 • Published • 34 -
FlowMind: Automatic Workflow Generation with LLMs
Paper • 2404.13050 • Published • 34 -
List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs
Paper • 2404.16375 • Published • 18 -
Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts
Paper • 2405.19893 • Published • 34 -
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
Paper • 2406.04325 • Published • 74 -
THEANINE: Revisiting Memory Management in Long-term Conversations with Timeline-augmented Response Generation
Paper • 2406.10996 • Published • 35 -
Scaling Synthetic Data Creation with 1,000,000,000 Personas
Paper • 2406.20094 • Published • 107 -
Wolf: Captioning Everything with a World Summarization Framework
Paper • 2407.18908 • Published • 32 -
Coarse Correspondence Elicit 3D Spacetime Understanding in Multimodal Language Model
Paper • 2408.00754 • Published • 23 -
Integrating Large Language Models into a Tri-Modal Architecture for Automated Depression Classification
Paper • 2407.19340 • Published • 58 -
Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
Paper • 2408.06195 • Published • 73 -
Controllable Text Generation for Large Language Models: A Survey
Paper • 2408.12599 • Published • 65 -
ART: Automatic multi-step reasoning and tool-use for large language models
Paper • 2303.09014 • Published • 1 -
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Paper • 2409.12183 • Published • 39 -
ProgCo: Program Helps Self-Correction of Large Language Models
Paper • 2501.01264 • Published • 26 -
Revisiting In-Context Learning with Long Context Language Models
Paper • 2412.16926 • Published • 32 -
Outcome-Refining Process Supervision for Code Generation
Paper • 2412.15118 • Published • 19 -
SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
Paper • 2412.11605 • Published • 18 -
OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
Paper • 2411.14199 • Published • 34 -
Natural Language Reinforcement Learning
Paper • 2411.14251 • Published • 31 -
HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
Paper • 2411.02959 • Published • 71 -
Search-o1: Agentic Search-Enhanced Large Reasoning Models
Paper • 2501.05366 • Published • 103 -
OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
Paper • 2501.09751 • Published • 46 -
PaSa: An LLM Agent for Comprehensive Academic Paper Search
Paper • 2501.10120 • Published • 55 -
Evolving Deeper LLM Thinking
Paper • 2501.09891 • Published • 115 -
Chain-of-Retrieval Augmented Generation
Paper • 2501.14342 • Published • 58 -
SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model
Paper • 2501.18636 • Published • 31 -
Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?
Paper • 2502.00674 • Published • 13 -
Large Language Model Guided Self-Debugging Code Generation
Paper • 2502.02928 • Published • 13 -
UltraIF: Advancing Instruction Following from the Wild
Paper • 2502.04153 • Published • 24 -
Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization
Paper • 2502.04295 • Published • 13 -
CoS: Chain-of-Shot Prompting for Long Video Understanding
Paper • 2502.06428 • Published • 10 -
SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models
Paper • 2502.09604 • Published • 37 -
SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models
Paper • 2502.09390 • Published • 16 -
ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation
Paper • 2502.09411 • Published • 22 -
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
Paper • 2502.14802 • Published • 13 -
Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents
Paper • 2502.16069 • Published • 20 -
Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis
Paper • 2502.14767 • Published • 7 -
HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs
Paper • 2503.02003 • Published • 48 -
LettuceDetect: A Hallucination Detection Framework for RAG Applications
Paper • 2502.17125 • Published • 13 -
CoSTAast: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing
Paper • 2503.10613 • Published • 79 -
GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing
Paper • 2503.10639 • Published • 53 -
Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching
Paper • 2503.05179 • Published • 46 -
Automated Movie Generation via Multi-Agent CoT Planning
Paper • 2503.07314 • Published • 44 -
Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning
Paper • 2503.04973 • Published • 27 -
CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance
Paper • 2503.10391 • Published • 12 -
WildIFEval: Instruction Following in the Wild
Paper • 2503.06573 • Published • 14 -
AI-native Memory 2.0: Second Me
Paper • 2503.08102 • Published • 13 -
ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation
Paper • 2503.21729 • Published • 29 -
Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking
Paper • 2503.19855 • Published • 29 -
Defeating Prompt Injections by Design
Paper • 2503.18813 • Published • 25 -
MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding
Paper • 2503.13964 • Published • 20 -
MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search
Paper • 2503.20757 • Published • 11 -
ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations
Paper • 2504.00824 • Published • 43 -
WikiVideo: Article Generation from Multiple Videos
Paper • 2504.00939 • Published • 37 -
ReZero: Enhancing LLM search ability by trying one-more-time
Paper • 2504.11001 • Published • 16 -
Reasoning Models Can Be Effective Without Thinking
Paper • 2504.09858 • Published • 12