Monte Carlo tree search
PulseAugur coverage of Monte Carlo tree search — every cluster mentioning Monte Carlo tree search across labs, papers, and developer communities, ranked by signal.
- instance of CatalyzeX Code Finder for Papers 90%
- used by multi-agent system 80%
- developed alphaXiv 70%
- developed ScienceCast 70%
- used by Gotit.pub 70%
- used by CatalyzeX 70%
- instance of alphaXiv 70%
- instance of ScienceCast 70%
- instance of Gotit.pub 70%
- used by CatalyzeX Code Finder for Papers 70%
- used by CORE Recommender 70%
- instance of CatalyzeX 60%
- 2026-05-08 research_milestone A new paper presents a finite-time analysis for MCTS in continuous POMDP planning, offering theoretical guarantees. source
10 day(s) with sentiment data
-
New MCTS-SFT framework enhances LLM Verilog generation
Researchers have developed MCTS-SFT, a novel framework designed to improve the generation of Verilog code by large language models. This method utilizes Monte Carlo Tree Search (MCTS) to guide the curation of reasoning …
-
New OrbitalGym simulator explores impact of planning vs. system design in satellite games
This paper introduces OrbitalGym, a JAX-based simulation environment designed to study adversarial encounters between satellites. The environment allows for large-scale parallel simulations on GPUs, enabling researchers…
-
New LLM-based method boosts knowledge base question answering efficiency
Researchers have developed a new method called M-ER to improve the efficiency of multi-hop knowledge base question answering (KBQA). This approach uses a large language model (LLM) integrated with Monte Carlo Tree Searc…
-
New benchmark assesses LLM ethics in multi-turn mental health support
Researchers have developed MindEth-Bench, a new benchmark designed to evaluate the ethical boundary adherence of large language models (LLMs) in multi-turn mental health support scenarios within the Chinese context. Unl…
-
New ReMCTS framework boosts LLM code generation accuracy
Researchers have developed ReMCTS, a novel framework that enhances code generation from large language models by integrating reflection-enhanced Monte Carlo Tree Search. This method improves the handling of hidden seman…
-
New DocSkill framework enhances multilingual document QA with adaptive reasoning
Researchers have introduced DocSkill, a new agentic framework designed to improve multilingual multi-hop document question answering. This framework utilizes a learned skill-orchestration policy to adaptively acquire an…
-
AlphaCNOT framework learns to minimize CNOT gates in quantum circuits
Researchers have developed AlphaCNOT, a novel reinforcement learning framework that utilizes Monte Carlo Tree Search to optimize quantum circuits. This model-based approach aims to minimize the number of CNOT gates, whi…
-
New pipeline mines multi-agent system design principles from workflow data
Researchers have developed a novel two-phase pipeline to systematically mine design principles from multi-agent systems (MAS). This approach repurposes an MCTS optimizer and a sandboxed AutoResearch loop to analyze a co…
-
ChemBART language model advances chemical synthesis planning
Researchers have developed ChemBART, a new language model based on BART, specifically designed for chemical synthesis planning. Unlike previous models that focused on single molecules, ChemBART uses a reaction-centric p…
-
New distributional MCTS algorithms improve risk-sensitive planning
Researchers have developed new distributional Monte-Carlo Tree Search (MCTS) algorithms, CATSO and PATSO, designed to handle risk-sensitive objectives like Conditional Value-at-Risk (CVaR). Unlike traditional MCTS which…
-
IneqAgent framework combines LLM reasoning with symbolic computation for inequality proving
Researchers have developed IneqAgent, a novel framework that merges Large Language Model (LLM) reasoning with symbolic computation to tackle complex inequality proving tasks within the Lean4 theorem prover. This agentic…
-
New CAR-MCTS algorithm offers deterministic guarantees for robust MDP planning
Researchers have developed CAR-MCTS, a novel Monte Carlo tree search algorithm designed for robust Markov decision process (MDP) planning. This new method provides the first deterministic anytime optimality guarantees f…
-
Monte Carlo Tree Search enhances financial regression feature selection
Researchers have developed a novel feature selection framework using Monte Carlo Tree Search (MCTS) with Generalized Nested Rollout Policy Adaptation (GNRPA) for high-dimensional financial regression. This method treats…
-
New SED-MCTS method enhances interpretability in PDE solution discovery
Researchers have developed SED-MCTS, a novel Monte Carlo tree search method designed to improve the interpretability and efficiency of discovering symbolic expressions for physical fields from observational data. Unlike…
-
MCTS performs worse than simpler methods for DAG workflow scheduling, study finds
A recent computational study comparing Monte Carlo Tree Search (MCTS) with a simpler randomized-restart list scheduling method for Directed Acyclic Graph (DAG) workflows found that MCTS performed worse. When both method…
-
Deep Ensemble improves AI path planning for oil spill monitoring
Researchers have developed a new method for informative path planning in aquatic environmental monitoring, specifically for scenarios like oil spills. This approach replaces traditional Gaussian Processes with a Deep En…
-
New DrugMCTS framework enhances drug repositioning with LLMs and multi-agent systems
Researchers have developed DrugMCTS, a new framework designed to improve drug repositioning using large language models. This system integrates retrieval-augmented generation (RAG), multi-agent collaboration, and Monte …
-
LLM agents enhance protein design with novel search framework
Researchers have developed ELMS (Evidence-based LLM-guided Monte Carlo Search), a novel framework for protein design that leverages Large Language Model (LLM) agents to improve motif scaffolding. Unlike traditional gene…
-
New frameworks enhance AI video understanding and multi-video reasoning · 3 sources tracked
Researchers have developed new frameworks for improving video understanding agents. Video-RSI focuses on recursive self-improvement by having agents revise their own harnesses to better acquire and use evidence from vid…
-
LLM inference reimagined with brain-inspired 'Programs-of-Layers'
Researchers have explored a novel approach to Large Language Model (LLM) inference, termed Programs-of-Layers (PoLar), which deviates from the standard fixed-depth forward pass. Inspired by the human brain's flexible in…