Abstract:Multi-step reasoning has proven essential for enhancing the problem-solving capabilities of Large Language Models (LLMs) by decomposing complex tasks into intermediate steps, either explicitly or implicitly. Extending the reasoning chain at test time through deeper thought processes or broader exploration, can furthur improve performance, but often incurs substantial costs due to the explosion in token usage. Yet, many reasoning steps are relatively simple and can be handled by more efficient smaller-scale language models (SLMs). This motivates hybrid approaches that allocate subtasks across models of varying capacities. However, realizing such collaboration requires accurate task decomposition and difficulty-aware subtask allocation, which is challenging. To address this, we propose R2-Reasoner, a novel framework that enables collaborative reasoning across heterogeneous LLMs by dynamically routing sub-tasks based on estimated complexity. At the core of our framework is a Reinforced Model Router, composed of a task decomposer and a subtask allocator. The task decomposer segments complex input queries into logically ordered subtasks, while the subtask allocator assigns each subtask to the most appropriate model, ranging from lightweight SLMs to powerful LLMs, balancing accuracy and efficiency. To train this router, we introduce a staged pipeline that combines supervised fine-tuning on task-specific datasets with Group Relative Policy Optimization algorithm, enabling self-supervised refinement through iterative reinforcement learning. Extensive experiments across four challenging benchmarks demonstrate that R2-Reasoner reduces API costs by 86.85% while maintaining or surpassing baseline accuracy. Our framework paves the way for more cost-effective and adaptive LLM reasoning. The code is open-source at https://anonymous.4open.science/r/R2_Reasoner .
Abstract:Chain-of-Thought (CoT) technique has proven effective in improving the performance of large language models (LLMs) on complex reasoning tasks. However, the performance gains are inconsistent across different tasks, and the underlying mechanism remains a long-standing research question. In this work, we make a preliminary observation that the monotonicity of token probability distributions may be correlated with the gains achieved through CoT reasoning. Leveraging this insight, we propose two indicators based on the token probability distribution to assess CoT effectiveness across different tasks. By combining instance-level indicators with logistic regression model, we introduce Dynamic CoT, a method that dynamically select between CoT and direct answer. Furthermore, we extend Dynamic CoT to closed-source models by transferring decision strategies learned from open-source models. Our indicators for assessing CoT effectiveness achieve an accuracy of 89.2\%, and Dynamic CoT reduces token consumption by more than 35\% while maintaining high accuracy. Overall, our work offers a novel perspective on the underlying mechanisms of CoT reasoning and provides a framework for its more efficient deployment.
Abstract:Large language model (LLM) agents have demonstrated strong capabilities across diverse domains. However, designing high-performing agentic systems remains challenging. Existing agent search methods suffer from three major limitations: (1) an emphasis on optimizing agentic workflows while under-utilizing proven human-designed components such as memory, planning, and tool use; (2) high evaluation costs, as each newly generated agent must be fully evaluated on benchmarks; and (3) inefficient search in large search space. In this work, we introduce a comprehensive framework to address these challenges. First, We propose a hierarchical search space that jointly models agentic workflow and composable functional components, enabling richer agentic system designs. Building on this structured design space, we introduce a predictive value model that estimates agent performance given agentic system and task description, allowing for efficient, low-cost evaluation during the search process. Finally, we present a hierarchical Monte Carlo Tree Search (MCTS) strategy informed by uncertainty to guide the search. Experiments on seven benchmarks, covering embodied, math, web, tool, and game, show that our method achieves an average performance gain of 8.34\% over state-of-the-art baselines and exhibits faster search progress with steeper improvement trajectories. Code repo is available at https://github.com/Ericccc02/AgentSwift.
Abstract:Modeling urban crime is an important yet challenging task that requires understanding the subtle visual, social, and cultural cues embedded in urban environments. Previous work has predominantly focused on rule-based agent-based modeling (ABM) and deep learning methods. ABMs offer interpretability of internal mechanisms but exhibit limited predictive accuracy.In contrast, deep learning methods are often effective in prediction but are less interpretable and require extensive training data. Moreover, both lines of work lack the cognitive flexibility to adapt to changing environments. Leveraging the capabilities of large language models (LLMs), we propose CrimeMind, a novel LLM-driven ABM framework for simulating urban crime within a multi-modal urban context.A key innovation of our design is the integration of the Routine Activity Theory (RAT) into the agentic workflow of CrimeMind, enabling it to process rich multi-modal urban features and reason about criminal behavior.However, RAT requires LLM agents to infer subtle cues in evaluating environmental safety as part of assessing guardianship, which can be challenging for LLMs. To address this, we collect a small-scale human-annotated dataset and align CrimeMind's perception with human judgment via a training-free textual gradient method.Experiments across four major U.S. cities demonstrate that CrimeMind outperforms both traditional ABMs and deep learning baselines in crime hotspot prediction and spatial distribution accuracy, achieving up to a 24% improvement over the strongest baseline.Furthermore, we conduct counterfactual simulations of external incidents and policy interventions and it successfully captures the expected changes in crime patterns, demonstrating its ability to reflect counterfactual scenarios.Overall, CrimeMind enables fine-grained modeling of individual behaviors and facilitates evaluation of real-world interventions.
Abstract:Driven by advances in Large Language Models (LLMs), integrating them into recommendation tasks has gained interest due to their strong semantic understanding and prompt flexibility. Prior work encoded user-item interactions or metadata into prompts for recommendations. In parallel, LLM reasoning, boosted by test-time scaling and reinforcement learning, has excelled in fields like mathematics and code, where reasoning traces and correctness signals are clear, enabling high performance and interpretability. However, directly applying these reasoning methods to recommendation is ineffective because user feedback is implicit and lacks reasoning supervision. To address this, we propose $\textbf{R2Rec}$, a reasoning-enhanced recommendation framework that samples interaction chains from the user-item graph and converts them into structured interaction-of-thoughts via a progressive masked prompting strategy, with each thought representing stepwise reasoning grounded in interaction context. This allows LLMs to simulate step-by-step decision-making based on implicit patterns. We design a two-stage training pipeline: supervised fine-tuning teaches basic reasoning from high-quality traces, and reinforcement learning refines reasoning via reward signals, alleviating sparse explicit supervision. Experiments on three real-world datasets show R2Rec outperforms classical and LLM-based baselines with an average $\textbf{10.48%}$ improvement in HitRatio@1 and $\textbf{131.81%}$ gain over the original LLM. Furthermore, the explicit reasoning chains enhance interpretability by revealing the decision process. Our code is available at: https://anonymous.4open.science/r/R2Rec-7C5D.
Abstract:The emergence of agentic recommender systems powered by Large Language Models (LLMs) represents a paradigm shift in personalized recommendations, leveraging LLMs' advanced reasoning and role-playing capabilities to enable autonomous, adaptive decision-making. Unlike traditional recommendation approaches, agentic recommender systems can dynamically gather and interpret user-item interactions from complex environments, generating robust recommendation strategies that generalize across diverse scenarios. However, the field currently lacks standardized evaluation protocols to systematically assess these methods. To address this critical gap, we propose: (1) an interactive textual recommendation simulator incorporating rich user and item metadata and three typical evaluation scenarios (classic, evolving-interest, and cold-start recommendation tasks); (2) a unified modular framework for developing and studying agentic recommender systems; and (3) the first comprehensive benchmark comparing 10 classical and agentic recommendation methods. Our findings demonstrate the superiority of agentic systems and establish actionable design guidelines for their core components. The benchmark environment has been rigorously validated through an open challenge and remains publicly available with a continuously maintained leaderboard~\footnote[2]{https://tsinghua-fib-lab.github.io/AgentSocietyChallenge/pages/overview.html}, fostering ongoing community engagement and reproducible research. The benchmark is available at: \hyperlink{https://huggingface.co/datasets/SGJQovo/AgentRecBench}{https://huggingface.co/datasets/SGJQovo/AgentRecBench}.
Abstract:Over the past year, the development of large language models (LLMs) has brought spatial intelligence into focus, with much attention on vision-based embodied intelligence. However, spatial intelligence spans a broader range of disciplines and scales, from navigation and urban planning to remote sensing and earth science. What are the differences and connections between spatial intelligence across these fields? In this paper, we first review human spatial cognition and its implications for spatial intelligence in LLMs. We then examine spatial memory, knowledge representations, and abstract reasoning in LLMs, highlighting their roles and connections. Finally, we analyze spatial intelligence across scales -- from embodied to urban and global levels -- following a framework that progresses from spatial memory and understanding to spatial reasoning and intelligence. Through this survey, we aim to provide insights into interdisciplinary spatial intelligence research and inspire future studies.
Abstract:LLMs as intelligent agents are being increasingly applied in scenarios where human interactions are involved, leading to a critical concern about whether LLMs are faithful to the variations in culture across regions. Several works have investigated this question in various ways, finding that there are biases present in the cultural representations of LLM outputs. To gain a more comprehensive view, in this work, we conduct the first large-scale evaluation of LLM culture assessing 20 countries' cultures and languages across ten LLMs. With a renowned cultural values questionnaire and by carefully analyzing LLM output with human ground truth scores, we thoroughly study LLMs' cultural alignment across countries and among individual models. Our findings show that the output over all models represents a moderate cultural middle ground. Given the overall skew, we propose an alignment metric, revealing that the United States is the best-aligned country and GLM-4 has the best ability to align to cultural values. Deeper investigation sheds light on the influence of model origin, prompt language, and value dimensions on cultural output. Specifically, models, regardless of where they originate, align better with the US than they do with China. The conclusions provide insight to how LLMs can be better aligned to various cultures as well as provoke further discussion of the potential for LLMs to propagate cultural bias and the need for more culturally adaptable models.
Abstract:The AgentSociety Challenge is the first competition in the Web Conference that aims to explore the potential of Large Language Model (LLM) agents in modeling user behavior and enhancing recommender systems on web platforms. The Challenge consists of two tracks: the User Modeling Track and the Recommendation Track. Participants are tasked to utilize a combined dataset from Yelp, Amazon, and Goodreads, along with an interactive environment simulator, to develop innovative LLM agents. The Challenge has attracted 295 teams across the globe and received over 1,400 submissions in total over the course of 37 official competition days. The participants have achieved 21.9% and 20.3% performance improvement for Track 1 and Track 2 in the Development Phase, and 9.1% and 15.9% in the Final Phase, representing a significant accomplishment. This paper discusses the detailed designs of the Challenge, analyzes the outcomes, and highlights the most successful LLM agent designs. To support further research and development, we have open-sourced the benchmark environment at https://tsinghua-fib-lab.github.io/AgentSocietyChallenge.
Abstract:Understanding human behavior and society is a central focus in social sciences, with the rise of generative social science marking a significant paradigmatic shift. By leveraging bottom-up simulations, it replaces costly and logistically challenging traditional experiments with scalable, replicable, and systematic computational approaches for studying complex social dynamics. Recent advances in large language models (LLMs) have further transformed this research paradigm, enabling the creation of human-like generative social agents and realistic simulacra of society. In this paper, we propose AgentSociety, a large-scale social simulator that integrates LLM-driven agents, a realistic societal environment, and a powerful large-scale simulation engine. Based on the proposed simulator, we generate social lives for over 10k agents, simulating their 5 million interactions both among agents and between agents and their environment. Furthermore, we explore the potential of AgentSociety as a testbed for computational social experiments, focusing on four key social issues: polarization, the spread of inflammatory messages, the effects of universal basic income policies, and the impact of external shocks such as hurricanes. These four issues serve as valuable cases for assessing AgentSociety's support for typical research methods -- such as surveys, interviews, and interventions -- as well as for investigating the patterns, causes, and underlying mechanisms of social issues. The alignment between AgentSociety's outcomes and real-world experimental results not only demonstrates its ability to capture human behaviors and their underlying mechanisms, but also underscores its potential as an important platform for social scientists and policymakers.