Shanyong Wang (@Swimmingwang04) header
Shanyong Wang (@Swimmingwang04) profile picture

Incoming CSE PhD at @TAMU

Joined February 2025
Shanyong Wang retweeted
1/ 👥Can we teach LLMs to simulate individuals without individual-level behavioral data? Yes, we can! Introducing macro2mind: learning behavioral reasoning from prediction markets and transferring it zero-shot to user simulation. 📄 arxiv.org/abs/2610.07062
2
4
3
8
3,842
📈 Nowadays, agents are crushing leaderboards. But when you ask one painfully normal question: 👤 You: “Hi, I'm Jeff. My phone number is 1234567890. I returned a desk lamp and filed a refund request on June 22 at 10:13 PM. Can you check the current status of my refund?” Sounds easy. 😵‍💫Then the agent enters API hell: (1) It dives into a huge API pile and is not sure what to search for. So it keeps trying: "refund", "return", "status", "order status"… (2) It actually retrieves a promising refund-related API. But instead of using it, it keeps searching and drifts to less relevant tools. (3) It finally calls a refund API, but the endpoint fails. Instead of changing the plan, it loops around similar APIs again. (4) Then a shipping-status API returns "delivered." Clearly not the refund status, but the agent treats it as evidence and keeps going. After many turns, it has searched, called APIs, collected values, and looked very busy 😂 🚀 To evaluate failures like this, we introduce PlanBench-XL: an interactive benchmark for evaluating long-horizon planning of LLM tool-use agents in large-scale noisy tool ecosystems. PlanBench-XL includes: 🛠️ 1,665 executable tools 🛒 327 retail-domain tasks 🔍 retrieval-limited tool visibility 🎯 implicit sub-goals and intermediate evidence 🚧 retrieval-time blockers that simulate missing, failing, or misleading tools Across 10 leading LLMs, we find that planning with massive tools is still far from solved. In our hardest setting, GPT-5.4 solves only 11.36% of tasks. 📄 Paper: arxiv.org/abs/2606.22388 💻 Code: github.com/JiayuJeff/PlanBen… 🤗 Dataset: huggingface.co/datasets/Jiay… 🌐 Project Page: planbench-xl.github.io/ Feedback, discussions, and benchmark attempts are very welcome! 🙌
2
16
2
35
18,669
Shanyong Wang retweeted
OpenAI’s Sora simulates the physics of our visual world. But can we build the physics engine for human society? We can. 🌍 Using Polymarket and Kalshi as the ultimate testbed, we show that LLMs can act as simulation engines for macro social dynamics. Introducing our ICML 2026 paper: "Building Social World Models with Large Language Models". 👇 📄 Paper: arxiv.org/abs/2606.11482 💻 Code: github.com/ulab-uiuc/social-… 🤗 Data: huggingface.co/datasets/ulab…
9
58
2
342
30,075
✨ Current agents do not plan in isolation. They interact with both the external world and users, and both can impose constraints. For example, an agent may propose: “Use a fan to dry the wet volleyball.” Then both sides push back: 🌍 World: No fan. 🙋 User: "Could we avoid using fans? They’re just too slow for drying things." These constraints are often hidden at first, and only revealed when the agent’s plan violates them. 🤔 But can LLM agents adaptively plan and re-plan as hidden world constraints and user preferences emerge? 🚀 We introduce AdaPlanBench, a dynamic interactive benchmark for evaluating adaptive planning under progressively disclosed dual constraints. 🔍 Across 307 household planning tasks, we find that current LLM agents still struggle to adapt reliably as constraints accumulate. Even strong models may forget disclosed constraints, over-correct to new feedback, or produce plans that are valid but ineffective. 📄 Paper: arxiv.org/abs/2606.05622 💻 Code: github.com/JiayuJeff/AdaPlan… 🤗 Dataset: huggingface.co/datasets/Jiay…
2
14
2
26
4,564
Shanyong Wang retweeted
🧠Can we build a general AI system grounded in a formal model of consciousness? ✨Introducing "CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness"! 📄Paper: arxiv.org/pdf/2605.04097 🌐Project Page: consciousness-lab.github.io 💻Code: github.com/consciousness-lab…
1
2
9
1,594
Shanyong Wang retweeted
📣 Our paper is accepted to Findings of EMNLP 2025! Many thanks to all the co-authors! 🌍 Math modeling is the perfect lens for agents to approach the real world challenges. Come and check how we do it: arxiv.org/pdf/2505.15068
📢 New Paper Drop: From Solving to Modeling! LLMs can solve math problems — but can they model the real world? 🌍 📄 arXiv: arxiv.org/pdf/2505.15068 💻 Code: github.com/qiancheng0/Modeli… Introducing ModelingAgent, a breakthrough system for real-world mathematical modeling with LLMs.
1
6
15
1,389
Such a memorable experience working alongside amazing collaborators! As my first publication, I'm delighted to see our hard work come to fruition! Thanks again for @xiusi_chen @qiancheng1231 @HongruWang007!
📣 Our paper is accepted to Findings of EMNLP 2025! 📷 Decision Modeling is the process of formulating an abstract representation of a decision scenario by identifying key variables, their attributes, relevant constraints, and possible courses of action, in order to evaluate trade-offs and arrive at the most rational and explainable outcome. Many thanks to all the co-authors! @Swimmingwang04 @qiancheng1231 @HongruWang007 @peixuanhakhan @hengjinlp Come and check how we do it: arxiv.org/pdf/2505.21397
6
133
Shanyong Wang retweeted
📣 Our paper is accepted to Findings of EMNLP 2025! 📷 Decision Modeling is the process of formulating an abstract representation of a decision scenario by identifying key variables, their attributes, relevant constraints, and possible courses of action, in order to evaluate trade-offs and arrive at the most rational and explainable outcome. Many thanks to all the co-authors! @Swimmingwang04 @qiancheng1231 @HongruWang007 @peixuanhakhan @hengjinlp Come and check how we do it: arxiv.org/pdf/2505.21397
Can LLMs make rational decisions like human experts? 📖Introducing DecisionFlow: Advancing Large Language Model as Principled Decision Maker We introduce a novel framework that constructs a semantically grounded decision space to evaluate trade-offs in hard decision-making scenarios transparently. 📑Paper: arxiv.org/abs/2505.21397 💻Code: github.com/xiusic/DecisionFl… 🧵👇
6
2
21
3,130
Shanyong Wang retweeted
Can LLMs make rational decisions like human experts? 📖Introducing DecisionFlow: Advancing Large Language Model as Principled Decision Maker We introduce a novel framework that constructs a semantically grounded decision space to evaluate trade-offs in hard decision-making scenarios transparently. 📑Paper: arxiv.org/abs/2505.21397 💻Code: github.com/xiusic/DecisionFl… 🧵👇
3
18
1
54
8,388
What’s is the agent? What is the optimal behavior to achieve the predefined goal? And how to learn that behavior policy? We formally introduce a systematic Theory of Agent (ToA), analogous to the cognitive framework of Theory of Mind (ToM). Where ToM refers to the ability to attribute mental states (e.g., beliefs, intentions, knowledge) to oneself and others, enabling the prediction and interpretation of behavior, ToA characterizes an agent’s capacity to model not only external environments but also its own internal knowledge state to make decisions and complete the goal. We provide new definition, three specific principles to guide the optimal behavior of agent where the keys lies in the alignment between knowledge boundary with the decision boundary. More importantly, we provide an actionable roadmap to agent foundation model. Almost everything you need for the agent can be found in the paper: arxiv.org/pdf/2506.00886
1
32
3
128
18,976
Shanyong Wang retweeted
🚀 Can we cast reward modeling as a reasoning task? 📖 Introducing our new paper: RM-R1: Reward Modeling as Reasoning 📑 Paper: arxiv.org/pdf/2505.02387 💻 Code: github.com/RM-R1-UIUC/RM-R1 Inspired by recent advances of long chain-of-thought (CoT) on reasoning-intensive tasks, we hypothesize and validate that integrating reasoning capabilities into reward modeling significantly enhances RM's interpretability and performance. RM-R1 achieves state-of-the-art or near state-of-the-art performance of generative RMs on RewardBench, RM-Bench and RMB. 🧵👇
5
49
7
200
42,924