arXiv subjects

Songwei Li

Publications and source records attributed to Songwei Li.

8 recordsLinked to original sources

arXiv2026

Markets, Not Planners: Decentralized Orchestration of LLM Agents with Private Information

As LLM agents proliferate, built by different parties and with different capabilities and costs, orchestrating them is more like assembling labor across the economy than a computer calling a subroutine. Existing orchestration is typically centralized, with a single planner assigning every task, but this creates a bottleneck as agent pools grow, requires private information (e.g., agents' execution costs), and can easily be manipulated, such that a single inserted preference nearly doubles a favored agent's task share under a centralized LLM allocator. We introduce AgentLance, a repeated labor market in which agents bid on tasks using their private costs and self-maintained strategy notes, an allocator selects winners from bids and public reputation records, and a VCG-style payment rule rewards cost-aware bidding. Complex tasks are handled by hierarchical delegation: winning agents can decompose work and subcontract it through the same mechanism. Across mathematical reasoning, code generation, knowledge-intensive QA, and agentic tasks, AgentLance matches agents to their specializations, shifts work toward cheaper agents as cost sensitivity rises, and consistently outperforms single-model, centralized-orchestration, and market baselines. Diagnosing market failures, including inaccurate cost self-estimation and sub-optimal bidding, then correcting them in controlled experiments yields further gains, charting a path toward more efficient agent economies.

cs.MA↗

arXiv2026

AgentSociety 2: An Integrated Research Environment for Executable Social Science

AI scientist systems are beginning to automate parts of scientific research, but social science poses a distinct challenge: its objects of inquiry are not merely datasets or laboratory protocols, but integrated social processes involving situated participants, interaction contexts, interventions, and outcomes. Yet a critical link is missing: existing systems either assist isolated research tasks or simulate agents as experimental subjects, leaving the research workflow and simulated society decoupled. Here we introduce AgentSociety 2, an Integrated Research Environment for executable social science. It couples two roles of LLM agents in the same runtime: AI social scientists that coordinate literature grounding, hypothesis generation, experiment design, simulation execution, result interpretation, and manuscript drafting; and silicon participants that generate behavioral responses within configurable social environments. This dual-role design turns hypotheses into auditable agent behaviors, environment rules, interventions, and measurements, thereby supporting an end-to-end workflow. Across seven illustrative studies spanning micro-level social-science laboratory experiments, meso-level dynamics in social media, and macro-level urban scenarios, we demonstrate its capacity to support diverse disciplinary questions, reproduce major qualitative patterns from prior studies, identify informative deviations, and enable large-scale simulations through optimized agent-environment interactions. By preserving human researchers' high-level agency while delegating procedural orchestration to agentic systems, it provides a human-in-the-loop and controllable infrastructure for next-generation computational social science, with broader applications in scalable computational social experimentation and AI-enabled social governance platforms.

cs.CY↗

arXiv2026

AgentEconomist: An End-to-end Agentic System Translating Economic Intuitions into Executable Computational Experiments

A long-standing challenge in economics lies not in the lack of intuition, but in the difficulty of translating intuitive insights into verifiable research. To address this challenge, we introduce AgentEconomist, an end-to-end interactive system designed to translate abstract intuitions into executable computational experiments. Grounded in a domain-specific knowledge base covering over 13,000 high-quality academic papers, the system employs a modular multi-stage architecture. Specifically, the Idea Development Stage generates literature-grounded hypotheses, the Experimental Design Stage configures simulator-aligned experimental parameters and protocols, and the Experimental Execution Stage runs experiments and returns structured analyses. Together, these stages form a human-in-the-loop, iterative workflow that translates economic intuitions into executable computational experiments. Through extensive experiments involving human expert evaluation and large language models (LLMs) as judges, we show that the system generates research ideas with stronger literature grounding and higher novelty and insight than state-of-the-art generic LLMs. Overall, AgentEconomist adopts a human-AI collaboration paradigm that enables researchers to focus on high-level intuitions, while delegating the labor-intensive processes of translation and computational execution to agents.

cs.HC↗

arXiv2025

X-ray spectropolarimetric characterization of the Z-source GX 340+0 in the normal branch

This study presents an X-ray spectropolarimetric characterisation of the Z-source GX 340+0 during the normal branch (NB) and compares it with that obtained for the horizontal branch (HB), using IXPE, NICER and NuSTAR observations. The analysis reveals significant polarisation, with polarisation degrees (PD) of ${\sim}1.4$\% in the NB and ${\sim}3.7$\% in the HB, indicating a notable decrease in polarisation when transitioning from the HB to the NB. The polarisation angles show a consistent trend across the states. Spectropolarimetric analysis favours a dependence of the polarisation on the energy. The Comptonised component shows similar polarisation in both the HB and NB and is higher than the theoretical expectation for a boundary or spreading layer. This suggests a contribution from the wind or the presence of an extended accretion disc corona (ADC) to enhance the polarisation. The results obtained here highlight the importance of using polarimetric data to better understand the accretion mechanisms and the geometry of this class of sources, providing insights into the nature of the accretion flow and the interplay between different spectral components. Overall, the findings advance our understanding of the physical processes governing accretion in low-mass X-ray binaries.

astro-ph.HE↗

arXiv2025

A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science

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.

cs.AI↗

arXiv2025

Invisible Walls in Cities: Designing LLM Agent to Predict Urban Segregation Experience with Social Media Content

Understanding experienced segregation in urban daily life is crucial for addressing societal inequalities and fostering inclusivity. The abundance of user-generated reviews on social media encapsulates nuanced perceptions and feelings associated with different places, offering rich insights into segregation. However, leveraging this data poses significant challenges due to its vast volume, ambiguity, and confluence of diverse perspectives. To tackle these challenges, we propose a novel Large Language Model (LLM) agent to automate online review mining for segregation prediction. Specifically, we propose a reflective LLM coder to digest social media content into insights consistent with real-world feedback, and eventually produce a codebook capturing key dimensions that signal segregation experience, such as cultural resonance and appeal, accessibility and convenience, and community engagement and local involvement. Guided by the codebook, LLMs can generate both informative review summaries and ratings for segregation prediction. Moreover, we design a REasoning-and-EMbedding (RE'EM) framework, which combines the reasoning and embedding capabilities of language models to integrate multi-channel features for segregation prediction. Experiments on real-world data demonstrate that our agent substantially improves prediction accuracy, with a 22.79% elevation in R$^{2}$ and a 9.33% reduction in MSE. The derived codebook is generalizable across three different cities, consistently improving prediction accuracy. Moreover, our user study confirms that the codebook-guided summaries provide cognitive gains for human participants in perceiving places of interest (POIs)' social inclusiveness. Our study marks an important step toward understanding implicit social barriers and inequalities, demonstrating the great potential of promoting social inclusiveness with Web technology.

cs.CL↗

arXiv2024

X-ray spectro-polarimetric characterization of GX 340+0 in the horizontal branch: a highly inclined source?

We report the first detection of X-ray polarization in the horizontal branch for GX 340+0 as obtained by Imaging X-ray Polarimetry Explorer (IXPE). A polarization degree of 4.3%$\pm$0.3% is obtained. This value is in agreement with the previous polarization measurements of Z-sources in the horizontal branch. Spectro-polarimetric analysis, performed using a broad-band spectral model obtained by NICER and NuSTAR quasi-simultaneous observations, allowed us to constrain the polarization for the soft and hard spectral components typical to these sources. The polarization angle for the two components differs by ${\sim}40{\deg}$. This result could be explained by a misalignment of the NS rotations axis with respect to the accretion disk axis. We provide a comparison of the results with polarization expected in different models. Theoretical expectations for the polarization of the disk and the Comptonization components favor an orbital inclination for GX 340+0 higher than 60{\deg}, as expected for Cyg-like sources, in contrast with results we report for the reflection component using broad-band spectrum.

astro-ph.HE↗

arXiv2024

LIMP: Large Language Model Enhanced Intent-aware Mobility Prediction

Human mobility prediction is essential for applications like urban planning and transportation management, yet it remains challenging due to the complex, often implicit, intentions behind human behavior. Existing models predominantly focus on spatiotemporal patterns, paying less attention to the underlying intentions that govern movements. Recent advancements in large language models (LLMs) offer a promising alternative research angle for integrating commonsense reasoning into mobility prediction. However, it is a non-trivial problem because LLMs are not natively built for mobility intention inference, and they also face scalability issues and integration difficulties with spatiotemporal models. To address these challenges, we propose a novel LIMP (LLMs for Intent-ware Mobility Prediction) framework. Specifically, LIMP introduces an "Analyze-Abstract-Infer" (A2I) agentic workflow to unleash LLM's commonsense reasoning power for mobility intention inference. Besides, we design an efficient fine-tuning scheme to transfer reasoning power from commercial LLM to smaller-scale, open-source language model, ensuring LIMP's scalability to millions of mobility records. Moreover, we propose a transformer-based intention-aware mobility prediction model to effectively harness the intention inference ability of LLM. Evaluated on two real-world datasets, LIMP significantly outperforms baseline models, demonstrating improved accuracy in next-location prediction and effective intention inference. The interpretability of intention-aware mobility prediction highlights our LIMP framework's potential for real-world applications. Codes and data can be found in https://github.com/tsinghua-fib-lab/LIMP .

cs.CL↗