Related papers: Levin Tree Search with Context Models

Reinforcement Learning with Verifiable Rewards (RLVR) has established itself as the dominant paradigm for instilling rigorous reasoning capabilities in Large Language Models. While effective at amplifying dominant behaviors, we identify a…

It is known that the Thresholded Lasso (TL), SCAD or MCP correct intrinsic estimation bias of the Lasso. In this paper we propose an alternative method of improving the Lasso for predictive models with general convex loss functions which…

Monte Carlo Tree Search (MCTS) is a powerful approach to designing game-playing bots or solving sequential decision problems. The method relies on intelligent tree search that balances exploration and exploitation. MCTS performs random…

In this paper, we propose an explicit, non-strict representation of search trees in constraint-logic object-oriented programming. Our search tree representation includes both the non-deterministic and deterministic behaviour during…

This study investigates the combined use of generative grammar rules and Monte Carlo Tree Search (MCTS) for optimizing truss structures. Our approach accommodates intermediate construction stages characteristic of progressive construction…

Most Probable Explanation (MPE) inference in Probabilistic Graphical Models (PGMs) is a fundamental yet computationally challenging problem arising in domains such as diagnosis, planning, and structured prediction. In many practical…

We present an algorithm for local, regularized, policy improvement in reinforcement learning (RL) that allows us to formulate model-based and model-free variants in a single framework. Our algorithm can be interpreted as a natural extension…

This paper presents a novel approach to solving convex optimization problems by leveraging the fact that, under certain regularity conditions, any set of primal or dual variables satisfying the Karush-Kuhn-Tucker (KKT) conditions is…

Due to the large combinatorial problem, current beam orientation optimization algorithms for radiotherapy, such as column generation (CG), are typically heuristic or greedy in nature, leading to suboptimal solutions. We propose a…

Sequential decision-making under uncertainty is present in many important problems. Two popular approaches for tackling such problems are reinforcement learning and online search (e.g., Monte Carlo tree search). While the former learns a…

We introduce a recursive AlphaZero-style Monte--Carlo tree search algorithm, "RMCTS". The advantage of RMCTS over AlphaZero's MCTS-UCB is speed. In RMCTS, the search tree is explored in a breadth-first manner, so that network inferences…

Large Language Models (LLMs) have demonstrated impressive performance across various tasks. However, current training approaches combine standard cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance…

Finding a concise and interpretable mathematical formula that accurately describes the relationship between each variable and the predicted value in the data is a crucial task in scientific research, as well as a significant challenge in…

Recent advancements in large language models (LLMs) have sparked considerable interest in automated theorem proving and a prominent line of research integrates stepwise LLM-based provers into tree search. In this paper, we introduce a novel…

Vector similarity search plays a pivotal role in modern information retrieval systems, especially when powered by transformer-based embeddings. However, the scalability and efficiency of such systems are often hindered by the high…

Large language models (LLMs) have achieved remarkable multi-step reasoning capabilities across various domains. However, LLMs still face distinct challenges in complex logical reasoning, as (1) proof-finding requires systematic exploration…

Competition-level code generation tasks pose significant challenges for current state-of-the-art large language models (LLMs). For example, on the LiveCodeBench-Hard dataset, models such as O1-Mini and O1-Preview achieve pass@1 rates of…

We propose SC-MCTS*: a novel Monte Carlo Tree Search (MCTS) reasoning algorithm for Large Language Models (LLMs), significantly improves both reasoning accuracy and speed. Our motivation comes from: 1. Previous MCTS LLM reasoning works…

LLM-powered systems require complex multi-step decision-making abilities to solve real-world tasks, yet current planning approaches face a trade-off between the high latency of inference-time search and the limited generalization of…

Large language models (LLMs) are increasingly used in modern search and answer systems to synthesize multiple, sometimes conflicting, texts into a single response, yet current pipelines offer weak incentives for sources to be accurate and…