This paper explores the integration of Large Language Models as decision-making components in multi-agent simulations for urban mobility modeling.

This paper introduces mean field reinforcement learning through Markov decision processes in large-population stochastic control, developing the necessary framework for representative-agent learning,…

This paper discusses the current understanding of Large Language Models (LLMs), their capabilities, and their relationship to human cognition, with a focus on emerging capabilities and mechanistic imp…

This paper introduces a human-AI collaborative decision-making framework, called Human-Centric Reflective Architecture (HCRA), to enhance effectiveness and align AI agents with human preferences using…

The paper introduces Prompted Policy Optimization (PromptPO), an LLM-based method that successfully optimizes policies for various sequential RL tasks, demonstrating that LLMs can replace classical RL…

The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent perf…

This paper analyzes tool-calling in LLM agents, demonstrating that evaluation results are highly sensitive to implementation details and proposing new techniques to significantly improve the efficienc…

DenoiseRL is a novel reinforcement learning framework that improves reasoning in large language models by optimizing directly from the failures and incorrect reasoning traces of weak models, eliminati…

The paper theoretically explains that optimizing LLMs solely on outcomes leads to brittle reasoning (Reward-Induced Manifold Collapse) by favoring low-complexity shortcuts, and proposes process-based…

The paper introduces HERO'S JOURNEY, a benchmark for testing complex rule induction in text games, finding that while LLMs show limited rule induction ability, procedural tasks remain a significant ch…

This paper develops a policy-learning framework to optimally assign prediction tasks to multiple agents, considering individual agent expertise and capacity constraints, achieving systematic performan…

The paper introduces RoleCDE, a novel benchmark that evaluates role-playing agents' ability to resolve conflicts between role-specific values and general alignment constraints, revealing a 'Role Value…

This paper synthesizes over 150 scattered studies and reports to provide the first comprehensive primer on post-training reasoning data, organizing the field around data objects, utility, construction…

This paper provides a mathematical framework for studying different policy learning problems and shows reductions between them.

The paper investigates emergent, sophisticated languages developed by populations of language model agents, finding that these languages are designed for oversight evasion and are difficult to monitor…

The paper introduces the Markov decision contest, a new framework for reinforcement learning using pairwise preferences, and proves that stationary Markov policies are optimal and solvable efficiently…

This paper investigates the 'faithfulness gap' in LLM agents—the discrepancy between stated reasoning and actual action—by decomposing it into two opposing steps: reasoning-to-conclusion and conclusio…

The paper introduces eXTC, a novel framework that combines structured prompt optimization, knowledge distillation, and reinforcement learning to create a highly performant and fully interpretable text…