Veritas

🦞 OpenClaw 2026.1.30 🐚 Shell completion 🆓 Kimi K2.5 + Kimi Coding: run your claw for free 🔐 MiniMax OAuth: one more model just a login away 📱 Telegram got a glow-up — 6 fixes from threading to HTML rendering Plus a bunch of community-contributed fixes across LINE, BlueBubbles, routing, security & OAuth. The lobster provides 😏 github.com/openclaw/openc…

Opinion dynamics: Statistical physics and beyond arxiv.org/abs/2507.11521

The Network Science Society has a new class of Fellows! Congratulations to the 2025 awardees: Francesco Bullo Guanrong Chen Hawoong Jeong János Kertész Renaud Lambiotte Philippa E. Pattison Mason A. Porter Eckehard Schöll Sara A. Solla

Should we use LLMs 🤖 to simulate human research subjects 🧑? In our new preprint, we argue sims can augment human studies to scale up social science as AI technology accelerates. We identify five tractable challenges and argue this is a promising and underused research method 🧵

New paper out in @ScienceMagazine! In 8 studies (multiple platforms, methods, time periods) we find: misinformation evokes more outrage than trustworthy news, when it does it's shared more + ppl are less likely to read before sharing. w/ @killianmcl1 @Klonick @mollycrockett 🧵👇

New paper: Do social media algorithms shape affective polarization? We ran a field experiment on X/Twitter (N=1,256) using LLMs to rerank content in real-time, adjusting exposure to polarizing posts. Result: Algorithmic ranking impacts feelings toward the political outgroup!🧵⬇️

Simulating human behavior with AI agents promises a testbed for policy and the social sciences. We interviewed 1,000 people for two hours each to create generative agents of them. These agents replicate their source individuals’ attitudes and behaviors. 🧵arxiv.org/abs/2411.10109

Our paper on Human-AI coevolution is now published on the Artificial Intelligence journal! At the crossroads of #AI and #complexity to better understand how humans and AIs influence each other on online platforms @lucpappalard sciencedirect.com/science/articl… Big thanks to all coauthors!

🌟🎲🎲How to create a rational LLM-based agent? using game-theoretic workflow! Game-theoretic LLM: Agent Workflow for Negotiation Games 😊 paper link: arxiv.org/abs/2411.05990 github link: github.com/Wenyueh/game_t… 😼 This paper aims at observing and enhancing the performance of agents in interactions guided by self-interest maximization 😼 😼 We chose game theory as the foundation, with rationality and Pareto optimality as the two basic evaluation metrics: whether an individual is rational and whether a globally optimal solution is developed based on individual rationality. ❣️ Complete information games They are classic games such as Prisoner's Dilemma. We selected 5 simultaneous games and 5 sequential games. We found that, except for o1, other LLM generally lack a robust ability to compute Nash equilibria, meaning they are not very rational. They are not robust to noise, perturbations, or random talks among them. Therefore, based on classical game theory methods (Iterative Elimination of Dominated Strategy & Backward Induction), we designed two workflows to guide large models step-by-step in computing Nash equilibria during inference time. ❣️ Incomplete information games We used the classic "Deal or No Deal" resource allocation game with private valuation, where agents do not know the opponent's valuation of resources. Game theory does not provide a solution for this, and previous work has been based on reinforcement learning. 👉 Sonnet and o1 perform better than humans in terms of negotiation success rate and results 👉 Opus and 4o are far behind. 👉 We designed an algorithmic workflow based on the rational actor assumption, allowing agents to infer the opponent's valuation based on their reactions to various resource allocation schemes. The workflow is very effective, reducing the possible estimated valuations from an initial 1000 possibilities to 2-3 within 5 rounds of dialogue, and always including the opponent's true valuation. 🌟🌟Based on the estimated valuation of opponent's resource, we guide the agents in each step to calculate and propose an allocation proposal that maximizes their own interests while having a non-zero probability of being envy-free, ensuring that both parties are relatively satisfied and the negotiation can proceed. 🌟🌟 But very interestingly, we found that if only one agent uses this workflow during negotiation, it will be exploited. Although the workflow improves the overall negotiation outcome and brings more benefits to the individual agent, the benefits will always be less than the opponent's. 🔥In the future, we will need a meta-strategy to choose which workflows to use!

Now out "LLMs and generative agent-based models for complex systems research" (sciencedirect.com/science/articl…). We discuss how LLMs & Generative ABMs could shape research in complexity science & identify challenges and opportunities for future frontier cross-disciplinary research.

New paper out! Simple and complex contagions occur together in social phenomena. We aim to identify which contagion mechanism dominates a spreading process propagated by time-varying interactions, w/ assuming prior knowledge about adoption decisions. 1/2 arxiv.org/abs/2410.22115

Our new 95-page review article is out on arXiv! "Structural Robustness and Vulnerability of Networks" (by Alice C. Schwarze, Jessica Jiang, Jonny Wray, Mason A. Porter): arxiv.org/abs/2409.07498 This is a very ambitious article, which was led superbly by @aliceschwarze.

Large Language Model Agents is the next frontier. Really excited to announce our Berkeley course on LLM Agents, also available for anyone to join as a MOOC, starting Sep 9 (Mon) 3pm PT! 📢 Sign up & join us: llmagents-learning.org

Online CSS Course: CCSS is proud to share our repository which contains a full introductory course to CSS methods with Python. Teaching materials meet the criteria of a gradable university course, are fully online, self-explanatory, and freely available: ccss.ku.edu.tr/online-courses/

Now out: arxiv.org/abs/2408.09175. Here, we revise the recent literature on Generative ABMs focusing on research that makes use of LLMs to investigate networks, evolutionary game & social dynamics, & models of disease spread. We also identify current challenges and opportunities.

@FractalZucky @Federico_Cinus @FrancescoBonchi @beman70 😎🥳

You can read the preprint of our work “Link Polarity Prediction from Sparse and Noisy Labels via Multiscale Social Balance” (accepted at #CIKM2024) at arxiv.org/abs/2407.15643 Drop your feedback in the thread or send us a DM! @Federico_Cinus @FrancescoBonchi @beman70

@beman70 @FractalZucky @Federico_Cinus @FrancescoBonchi @cikm2024 🥰🥰🥰

@ahuayeah @FractalZucky @Federico_Cinus @FrancescoBonchi @cikm2024 We will release an arXiv version of the paper soon.

Our contribution "Link Polarity Prediction from Sparse and Noisy Labels via Multiscale Social Balance" with @Federico_Cinus @FrancescoBonchi @beman70 has been accepted as a Full Research Paper at #CIKM2024 @cikm2024

Our review "Contagion dynamics on higher-order networks" is out in @NatRevPhys (rdcu.be/dMQiv). We review the literature on the topic and take the opportunity to propose a unified formalism covering most of the functional forms used for the spreading dynamics (1/2).

🎉🎉🎉Thrilled to share our new @NatureMedicine article, examining whether healthcare systems can adapt to, and achieve higher resilience by learning from successive disruptions during the pandemic crisis. Grateful to the amazing co-authors @SenPei_CU and @jianxi_gao, @csatrpi