2 citations · 6 across the 25 of their papers we have counts for
26 papers
Can Language Models Learn to Forecast Stock Prices
Jiacheng Guo, Suozhi Huang, Shuzhen Li +11
Post-training has been shown to significantly improve language models' performance on tasks with verifiable outcomes, including mathematical reasoning, software engineering, and co…
Breaking Planner Integrity Boundary: Enviroment State-Text Injection Attack on LLM-Driven Embodied Agents
Jiawei Liu, Jiacheng Guo, Tian Zhang +7
Large language model (LLM)-driven embodied agents rely on environment states to interpret scenes, generate high-level plans, and drive physical execution, making planner-visible st…
Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation
Jiawei Liu, Jiacheng Guo, Tian Zhang +4
Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can propagate from digital input…
AQuA: Recursively Self-Improving Quantitative Trading Research Agents
Jiacheng Guo, Suozhi Huang, Yunlong Gao +5
We study recursive self-improvement at the level of quantitative-investment research: whether an autonomous system can use evidence from earlier experiments to improve the hypothes…
DeepLoop: Depth Scaling for Looped Transformers
Shuzhen Li, Yifan Zhang, Jiacheng Guo +2
Looped Transformers scale sequential computation by applying a compact stack of physical blocks for multiple rounds, increasing unrolled depth without increasing stored parameters.…
Unsupervised Multi-agent and Single-agent Perception from Cooperative Views
Haochen Yang, Baolu Li, Lei Li +5
The LiDAR-based multi-agent and single-agent perception has shown promising performance in environmental understanding for robots and automated vehicles. However, there is no exist…
FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains
Jiashuo Liu, Siyuan Chen, Zaiyuan Wang +38
Building upon FutureX, which established a live benchmark for general-purpose future prediction, this report introduces FutureX-Pro, including FutureX-Finance, FutureX-Retail, Futu…
GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
Jiacheng Guo, Ling Yang, Peter Chen +6
Training capable Large Language Model (LLM) agents is critically bottlenecked by the high cost and static nature of real-world interaction data. We address this by introducing GenE…
CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency
Jiacheng Guo, Suozhi Huang, Zixin Yao +16
This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorously evaluate the real-world capabilities of Large Language Model (LLM) agents in t…
A Low-Rank Method for Vision Language Model Hallucination Mitigation in Autonomous Driving
Keke Long, Jiacheng Guo, Tianyun Zhang +2
Vision Language Models (VLMs) are increasingly used in autonomous driving to help understand traffic scenes, but they sometimes produce hallucinations, which are false details not…
Alita-G: Self-Evolving Generative Agent for Agent Generation
Jiahao Qiu, Xuan Qi, Hongru Wang +9
Large language models (LLMs) have been shown to perform better when scaffolded into agents with memory, tools, and feedback. Beyond this, self-evolving agents have emerged, but cur…
On the Role of Preference Variance in Preference Optimization
Jiacheng Guo, Zihao Li, Jiahao Qiu +2
Direct Preference Optimization (DPO) has emerged as an important approach for learning from human preferences in aligning large language models (LLMs). However, collecting human pr…
FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction
Zhiyuan Zeng, Jiashuo Liu, Siyuan Chen +28
Future prediction is a complex task for LLM agents, requiring a high level of analytical thinking, information gathering, contextual understanding, and decision-making under uncert…
On Path to Multimodal Historical Reasoning: HistBench and HistAgent
Jiahao Qiu, Fulian Xiao, Yimin Wang +96
Recent advances in large language models (LLMs) have led to remarkable progress across domains, yet their capabilities in the humanities, particularly history, remain underexplored…
AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes
Jiahao Qiu, Xinzhe Juan, Yimin Wang +11
While knowledge distillation has become a mature field for compressing large language models (LLMs) into smaller ones by aligning their outputs or internal representations, the dis…
Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution
Jiahao Qiu, Xuan Qi, Tongcheng Zhang +15
Recent advances in large language models (LLMs) have enabled agents to autonomously perform complex, open-ended tasks. However, many existing frameworks depend heavily on manually…
Temporal Consistency for LLM Reasoning Process Error Identification
Jiacheng Guo, Yue Wu, Jiahao Qiu +4
Verification is crucial for effective mathematical reasoning. We present a new temporal consistency method where verifiers iteratively refine their judgments based on the previous…
MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
Kaixuan Huang, Jiacheng Guo, Zihao Li +15
Large language models have demonstrated impressive performance on challenging mathematical reasoning tasks, which has triggered the discussion of whether the performance is achieve…
Stealthy Multi-Task Adversarial Attacks
Jiacheng Guo, Tianyun Zhang, Lei Li +3
Deep neural networks are highly vulnerable to adversarial perturbations, raising serious safety concerns in the real-world systems. While prior work mainly explores single-task att…
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
Jiahao Qiu, Yifu Lu, Yifan Zeng +9
Inference-time alignment enhances the performance of large language models without requiring additional training or fine-tuning but presents challenges due to balancing computation…
V2X-DGW: Domain Generalization for Multi-agent Perception under Adverse Weather Conditions
Baolu Li, Jinlong Li, Xinyu Liu +5
Current LiDAR-based Vehicle-to-Everything (V2X) multi-agent perception systems have shown the significant success on 3D object detection. While these models perform well in the tra…
Bifurcated Attention: Accelerating Massively Parallel Decoding with Shared Prefixes in LLMs
Ben Athiwaratkun, Sujan Kumar Gonugondla, Sanjay Krishna Gouda +10
This study introduces bifurcated attention, a method designed to enhance language model inference in shared-context batch decoding scenarios. Our approach addresses the challenge o…
EVD4UAV: An Altitude-Sensitive Benchmark to Evade Vehicle Detection in UAV
Huiming Sun, Jiacheng Guo, Zibo Meng +4
Vehicle detection in Unmanned Aerial Vehicle (UAV) captured images has wide applications in aerial photography and remote sensing. There are many public benchmark datasets proposed…
Tracking without Label: Unsupervised Multiple Object Tracking via Contrastive Similarity Learning
Sha Meng, Dian Shao, Jiacheng Guo +1
Unsupervised learning is a challenging task due to the lack of labels. Multiple Object Tracking (MOT), which inevitably suffers from mutual object interference, occlusion, etc., is…