Author name cluster

Junzhe Jiang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

TMLR Journal 2026 Journal Article

LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed

Chang Yang
Xinrun Wang
Junzhe Jiang
Qinggang Zhang
Xiao Huang

World model emerges as a key module in decision making, where MuZero and Dreamer achieve remarkable successes in complex tasks. Recent work leverages Large Language Models (LLMs) as general world simulators to simulate the dynamics of the world due to their generalizability. LLMs also serve as the world model for deliberative reasoning in Reasoning via Planning (RAP) and Tree of Thought (ToT). However, the world model is either evaluated as a general world simulator, or as a functional module of the agent, i.e., predicting the transitions to assist the planning. This paper argues that LLM-based world models can make decisions solely, but rigorous evaluations are needed. We first present the two key observations to showcase how LLM-based world models can make decisions solely, and then present the three key observations to demonstrate why current evaluation framework of LLM-based world models is not sufficient. Then, we present our suggested evaluation framework: policy verification, action proposal, and policy planning, where the world model is used for decision making solely, and finally we leverage the 31 diverse environments from (Wang et al., 2023; 2024) and curate the rule-based policy of each environment for diverse evaluations. The key findings include: i) GPT-4o significantly outperforms GPT-4o-mini on the three main tasks, especially for the tasks which require the domain knowledge, e.g., scientific tasks, ii) the performance of the LLM-based world models depends predominantly on their performance in key steps, while the total number of steps required for task completion is a weak indicator of task difficulty with critical bottleneck steps playing a more decisive role and iii) the combination of world models’ functionalities for decision making tends to increase performance instability in our experiments, which can partially obscure the performance gap between stronger and weaker model.

PDF Details

TMLR Journal 2026 Journal Article

Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMs

Chang Yang
Ruiyu Wang
Junzhe Jiang
Qi Jiang
Qinggang Zhang
Yanchen Deng
Shuxin Li
Shuyue Hu

Reasoning is the fundamental capability of large language models (LLMs). Due to the rapid progress of LLMs, there are two main issues of current benchmarks: i) these benchmarks can be crushed in a short time (less than 1 year), and ii) these benchmarks may be easily hacked. To handle these issues, we propose the ever-scalingness for building the benchmarks which are scaling over complexity, instance, oversight and coverage. This paper presents Nondeterministic Polynomial-time Problem Challenge (NPPC), an ever-scaling reasoning benchmark for LLMs. Specifically, the NPPC has three main modules: i) npgym, which provides a unified interface of 25 well-known NP-complete problems and can generate any number of instances with any levels of complexities, ii) npsolver, which provides a unified interface to evaluate the problem instances with both online and offline models via APIs and local deployments, respectively, and iii) npeval, which provides the comprehensive and ready-to-use tools to analyze the performances of LLMs over different problems, the number of tokens, the aha moments, the reasoning errors and the solution errors. Extensive experiments over widely-used LLMs demonstrate: i) NPPC can successfully decrease the performances of advanced LLMs to below 10%, demonstrating that NPPC is not crushed by current models, ii) DeepSeek-R1, Claude-3.7-Sonnet, and o1/o3-mini are the most powerful LLMs, where DeepSeek-R1 can outperform Claude-3.7-Sonnet and o1/o3-mini in most NP-complete problems considered, and iii) the numbers of tokens, aha moments in the advanced LLMs, e.g., Claude-3.7-Sonnet and DeepSeek-R1, are observed first to increase and then decrease when the problem instances become more and more difficult. Through continuously scaling analysis, NPPC can provide critical insights into LLMs' reasoning capabilities, exposing fundamental limitations and suggesting future directions for further improvements.

PDF Details

AAAI Conference 2025 Conference Paper

Intent Oriented Contrastive Learning for Sequential Recommendation

Wuhong Wang
Jianhui Ma
Yuren Zhang
Kai Zhang
Junzhe Jiang
Yihui Yang
Yacong Zhou
Zheng Zhang

Sequential recommendation aims to predict the next item a user is likely to interact with based on their historical interaction sequence. Capturing user intent is crucial in this process, as each interaction is typically driven by specific intentions (e.g., buying skincare products for skin maintenance, buying makeup for cosmetic purposes, etc.). However, users often have multiple, dynamically changing intents, making it challenging for models to accurately learn these intents when relying on the entire historical sequence as input. To address this, we propose a novel framework called Intent Oriented Contrastive Learning for Sequential Recommendation (IOCLRec). This framework begins by segmenting users’ sequential behaviors into multiple subsequences, which represent the coarse-grained intents of users at different points in their interaction history. These subsequences form the basis for the three contrastive learning modules within IOCLRec. The fine-grained intent contrastive learning module uncovers detailed intent representations, while the single-intent and multi-intent contrastive learning modules utilize intent-oriented data augmentation operators to capture the diverse intents of users. These three modules work synergistically, driving comprehensive performance optimization in intricate sequential recommendation scenarios. Our method has been extensively evaluated on four public datasets, demonstrating superior effectiveness.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Logic-Q: Improving Deep Reinforcement Learning-based Quantitative Trading via Program Sketch-based Tuning

Zhiming Li
Junzhe Jiang
Yushi Cao
Aixin Cui
Bozhi Wu
Bo Li
Yang Liu
Danny Dongning Sun

Deep reinforcement learning (DRL) has revolutionized quantitative trading (Q-trading) by achieving decent performance without significant human expert knowledge. Despite its achievements, we observe that the current state-of-the-art DRL models are still ineffective in identifying the market trends, causing them to miss good trading opportunity or suffer from large drawdowns when encountering market crashes. To address this limitation, a natural approach is to incorporate human expert knowledge in identifying market trends. Whereas, such knowledge is abstract and hard to be quantified. In order to effectively leverage abstract human expert knowledge, in this paper, we propose a universal logic-guided deep reinforcement learning framework for Q-trading, called Logic-Q. In particular, Logic-Q adopts the program synthesis by sketching paradigm and introduces a logic-guided model design that leverages a lightweight, plug-and-play market trend-aware program sketch to determine the market trend and correspondingly adjusts the DRL policy in a post-hoc manner. Extensive evaluations of two popular quantitative trading tasks demonstrate that Logic-Q can significantly improve the performance of previous state-of-the-art DRL trading strategies.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Towards Automatic Sampling of User Behaviors for Sequential Recommender Systems

Hao Zhang
Mingyue Cheng
Zhiding Liu
Junzhe Jiang

Sequential recommender systems (SRS) have gained increasing popularity due to their remarkable proficiency in capturing dynamic user preferences. In the current setup of SRS, a common configuration is to uniformly consider each historical behavior as a positive interaction. However, this setting has the potential to yield sub-optimal performance as each individual item often have a different impact on shaping the user's interests. Hence, in this paper, we propose a novel automatic sampling framework for sequential recommendation, named AutoSAM, to non-uniformly treat historical behaviors. Specifically, AutoSAM extends the conventional SRS framework by integrating an extra sampler to intelligently discern the skew distribution of the raw input, and then sample informative sub-sets to build more generalizable SRS. To tackle the challenges posed by non-differentiable sampling actions and to introduce multiple decision factors for sampling, we further design a novel reinforcement learning based method to guide the training of the sampler. Furthermore, we theoretically devise multi-objective sampling rewards including Future Prediction and Sequence Perplexity, and then optimize the whole framework in an end-to-end manner by combining the policy gradient. We conduct extensive experiments on benchmark recommendation models and four real-world datasets. The experimental results demonstrate the effectiveness of the proposed AutoSAM.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning

Nan Song
Junzhe Jiang
Jingyu Li
Xiatian Zhu
Li Zhang

Motion simulation, prediction and planning are foundational tasks in autonomous driving, each essential for modeling and reasoning about dynamic traffic scenarios. While often addressed in isolation due to their differing objectives, such as generating diverse motion states or estimating optimal trajectories, these tasks inherently depend on shared capabilities: understanding multi-agent interactions, modeling motion behaviors, and reasoning over temporal and spatial dynamics. Despite this underlying commonality, existing approaches typically adopt specialized model designs, which hinders cross-task generalization and system scalability. More critically, this separation overlooks the potential mutual benefits among tasks. Motivated by these observations, we propose UniMotion, a unified motion framework that captures shared structures across motion tasks while accommodating their individual requirements. Built on a decoder-only Transformer architecture, UniMotion employs dedicated interaction modes and tailored training strategies to simultaneously support these motion tasks. This unified design not only enables joint optimization and representation sharing but also allows for targeted fine-tuning to specialize in individual tasks when needed. Extensive experiments on the Waymo Open Motion Dataset (WOMD) demonstrate that joint training leads to robust generalization and effective task integration. With further fine-tuning, UniMotion achieves state-of-the-art performance across a range of motion tasks, establishing it as a versatile and scalable solution for autonomous driving.

PDF Details