Related papers: PRIME: Policy-Reinforced Iterative Multi-agent Exe…

Large language models (LLMs) demonstrate their promise in tackling complicated practical challenges by combining action-based policies with chain of thought (CoT) reasoning. Having high-quality prompts on hand, however, is vital to the…

Understanding a program's runtime reasoning behavior, meaning how intermediate states and control flows lead to final execution results, is essential for reliable code generation, debugging, and automated reasoning. Although large language…

As language models regularly make mistakes when solving math problems, automated identification of errors in the reasoning process becomes increasingly significant for their scalable oversight. In this paper, we introduce ProcessBench for…

As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks remain largely confined to structured or exam-style tasks that fall short of real-world…

Reinforcement learning with verifiable rewards improves reasoning in large language models (LLMs), but many methods still rely on large human-labeled datasets. While self-play reduces this dependency, it often lacks explicit planning and…

Large language models (LLMs) have proven to be highly effective for solving complex reasoning tasks. Surprisingly, their capabilities can often be improved by iterating on previously generated solutions. In this context, a reasoning plan…

Reasoning in Large Language Models (LLMs) often suffers from inefficient long chain-of-thought traces with redundant self-exploration and validation, which inflate computational costs and even degrade performance. Inspired by human…

Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scenarios requiring foresight and autonomous decision-making. In…

Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by…

We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph…

Large Language Models (LLMs) have demonstrated remarkable emergent capabilities, yet the robustness of their numerical reasoning remains an open question. While standard benchmarks evaluate LLM reasoning on complex problem sets using…

Robotic path planning problems are often NP-hard, and practical solutions typically rely on approximation algorithms with provable performance guarantees for general cases. While designing such algorithms is challenging, formally proving…

Table reasoning requires models to jointly perform comprehensive semantic understanding and precise numerical operations. Although recent large language model (LLM)-based methods have achieved promising results, most of them still rely on a…

Large Language Models (LLMs) often generate substantively relevant content but fail to adhere to formal constraints, leading to outputs that are conceptually correct but procedurally flawed. Traditional prompt refinement approaches focus on…

The development of autonomous machine learning (ML) agents capable of end-to-end data science workflows represents a significant frontier in artificial intelligence. These agents must orchestrate complex sequences of data analysis, feature…

There has been considerable divergence of opinion on the reasoning abilities of Large Language Models (LLMs). While the initial optimism that reasoning might emerge automatically with scale has been tempered thanks to a slew of…

The advancement of large language model (LLM) based agents has shifted AI evaluation from single-turn response assessment to multi-step task completion in interactive environments. We present an empirical study evaluating frontier AI models…

Large language models (LLMs) are increasingly integrated into high-stakes decision-making. Inspired by the theory of \emph{inattentional blindness} in human cognition, we investigate whether LLMs, trained on human-preferred corpora that…

Large language models (LLMs) have been shown to be capable of impressive few-shot generalisation to new tasks. However, they still tend to perform poorly on multi-step logical reasoning problems. Here we carry out a comprehensive evaluation…

Process-level Reward Models (PRMs) are crucial for complex reasoning and decision-making tasks, where each intermediate step plays an important role in the reasoning process. Since language models are prone to various types of errors during…