LATS integrates Monte Carlo Tree Search with language models using in-context learning, value functions, and self-reflection to achieve 92.7% pass@1 on HumanEval and competitive web navigation performance.
AAAI38(2024), https://arxiv.org/abs/2308.09687
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
TRI trains LLMs on goal-conditioned fill-in-the-middle tasks via PSM token rearrangement and symbolic verification to surgically repair erroneous CoT segments.
OPT-BENCH and OPT-Agent evaluate LLM self-optimization in large search spaces, showing stronger models improve via feedback but stay constrained by base capacity and below human performance.
MOSAIC generates executable scientific code without I/O test cases by combining student-teacher distillation with a consolidated context window to reduce hallucinations across subproblems.
MOSAIC is a training-free multi-agent LLM framework with rationale, coding, reflection, and debugging agents plus a consolidated context window that outperforms prior methods on scientific coding benchmarks.
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.
OS-Atlas, trained on the largest open-source cross-platform GUI grounding corpus of 13 million elements, outperforms prior open-source models on six benchmarks across mobile, desktop, and web platforms.
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.
AlgoSkill improves LLM algorithm design on programming benchmarks by framing it as verification-guided scheduling over a typed skill library with MCTS, outperforming direct generation and self-refinement.
Runtime-structured task decomposition reduces retry costs in agentic coding systems by up to 51.7% versus monolithic prompts by rerunning only failed subtasks on two software engineering workloads.
Recursive reasoning systems can represent their state via an epistemic state graph and terminate when the linearized order-gap is non-degenerate near the fixed point, providing a local condition for when the stopping rule is informative.
A survey that provides a taxonomy of methods for improving planning in LLM-based agents across task decomposition, plan selection, external modules, reflection, and memory.
A survey taxonomy of LLMs identifies three scaling crises and six efficiency paradigms while tracing the shift from generation to tool-using agents.
The paper identifies inadequately addressed challenges in optimizing task allocation, fostering robust reasoning through debates, managing layered context, enhancing memory, and applying multi-agent systems to blockchain.
citing papers explorer
-
Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
LATS integrates Monte Carlo Tree Search with language models using in-context learning, value functions, and self-reflection to achieve 92.7% pass@1 on HumanEval and competitive web navigation performance.
-
Imbuing Large Language Models with Bidirectional Logic for Robust Chain Repair
TRI trains LLMs on goal-conditioned fill-in-the-middle tasks via PSM token rearrangement and symbolic verification to surgically repair erroneous CoT segments.
-
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
OPT-BENCH and OPT-Agent evaluate LLM self-optimization in large search spaces, showing stronger models improve via feedback but stay constrained by base capacity and below human performance.
-
No Test Cases, No Problem: Distillation-Driven Code Generation for Scientific Workflows
MOSAIC generates executable scientific code without I/O test cases by combining student-teacher distillation with a consolidated context window to reduce hallucinations across subproblems.
-
MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding
MOSAIC is a training-free multi-agent LLM framework with rationale, coding, reflection, and debugging agents plus a consolidated context window that outperforms prior methods on scientific coding benchmarks.
-
GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis
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.
-
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents
OS-Atlas, trained on the largest open-source cross-platform GUI grounding corpus of 13 million elements, outperforms prior open-source models on six benchmarks across mobile, desktop, and web platforms.
-
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.
-
AlgoSkill: Learning to Design Algorithms by Scheduling Human-Like Skills
AlgoSkill improves LLM algorithm design on programming benchmarks by framing it as verification-guided scheduling over a typed skill library with MCTS, outperforming direct generation and self-refinement.
-
Runtime-Structured Task Decomposition for Agentic Coding Systems
Runtime-structured task decomposition reduces retry costs in agentic coding systems by up to 51.7% versus monolithic prompts by rerunning only failed subtasks on two software engineering workloads.
-
State Representation and Termination for Recursive Reasoning Systems
Recursive reasoning systems can represent their state via an epistemic state graph and terminate when the linearized order-gap is non-degenerate near the fixed point, providing a local condition for when the stopping rule is informative.
-
Understanding the planning of LLM agents: A survey
A survey that provides a taxonomy of methods for improving planning in LLM-based agents across task decomposition, plan selection, external modules, reflection, and memory.
-
LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems
A survey taxonomy of LLMs identifies three scaling crises and six efficiency paradigms while tracing the shift from generation to tool-using agents.
-
LLM Multi-Agent Systems: Challenges and Open Problems
The paper identifies inadequately addressed challenges in optimizing task allocation, fostering robust reasoning through debates, managing layered context, enhancing memory, and applying multi-agent systems to blockchain.