1 citations · 2 across the 16 of their papers we have counts for
18 papers
Who Improves the Robot? Toward Physical Recursive Self-Improvement
Hai Zhou, Fan Yang, Zeyi Chen +27
Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive Self-Improvement (Physical RSI)…
Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents
Junyu Guo, Shangding Gu, Ming Jin +1
Coding agents can return plausible patches that omit required behavior. These failures are hard to review because long traces and confident summaries often hide what was missed. We…
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
Peizhi Niu, Wenjie Qu, Shangding Gu +14
Claw-like AI agents (e.g., OpenClaw) are always-on processes with persistent access to credentials, files, tools, and external services. They take on system-level responsibilities…
AION: Next-Generation Tasks and Practical Harness for Time Series
Tianxiang Zhan, Xiaobao Song, Tong Guan +2
Time series research is moving beyond fixed forecasting benchmarks toward realistic tasks that combine prediction, contextual reasoning, tool use, and structured decision support.…
Memory-Induced Tool-Drift in LLM Agents
Mahavir Dabas, Jihyun Jeong, Ming Jin +1
LLM agents increasingly combine long-term memory for personalization with tool calling for taking actions. We study a failure of this combination: personality-driven preferences st…
MemGym: a Long-Horizon Memory Environment for LLM Agents
Wujiang Xu, Yu Wang, Kai Mei +8
Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-…
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Ahmad Al-Tawaha, Shangding Gu, Peizhi Niu +2
Safety evaluations of memory-equipped LLM agents typically measure within-task safety: whether an agent completes a single scenario safely, often under adversarial conditions such…
LLMs Should Express Uncertainty Explicitly
Junyu Guo, Shangding Gu, Ming Jin +2
Large language models (LLMs) often produce confident yet incorrect answers, which can lead to risky failures in real-world applications. We study whether post-training can make a m…
AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond
Shangding Gu, Xiaohan Wang, Donghao Ying +9
Rapid advances in multimodal models demand benchmarks that rigorously evaluate understanding and reasoning in safety-critical, dynamic real-world settings. We present AccidentBench…
StyleBench: Evaluating thinking styles in Large Language Models
Junyu Guo, Shangding Gu, Ming Jin +2
Structured reasoning can improve the inference performance of large language models (LLMs), but it also introduces computational cost and control constraints. When additional reaso…
Agentic Web: Weaving the Next Web with AI Agents
Yingxuan Yang, Mulei Ma, Yuxuan Huang +15
The emergence of AI agents powered by large language models (LLMs) marks a pivotal shift toward the Agentic Web, a new phase of the internet defined by autonomous, goal-driven inte…
Few-Shot Test-Time Optimization Without Retraining for Semiconductor Recipe Generation and Beyond
Shangding Gu, Donghao Ying, Ming Jin +4
We introduce Model Feedback Learning (MFL), a novel test-time optimization framework for optimizing inputs to pre-trained AI models or deployed hardware systems without requiring a…
Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning
Shangding Gu, Laixi Shi, Muning Wen +5
Driven by inherent uncertainty and the sim-to-real gap, robust reinforcement learning (RL) seeks to improve resilience against the complexity and variability in agent-environment s…
Don't Trade Off Safety: Diffusion Regularization for Constrained Offline RL
Junyu Guo, Zhi Zheng, Donghao Ying +4
Constrained reinforcement learning (RL) seeks high-performance policies under safety constraints. We focus on an offline setting where the agent has only a fixed dataset -- common…
Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
Shangding Gu, Laixi Shi, Yuhao Ding +4
Safe reinforcement learning (RL) is crucial for deploying RL agents in real-world applications, as it aims to maximize long-term rewards while satisfying safety constraints. Howeve…
Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning
Shangding Gu, Bilgehan Sel, Yuhao Ding +4
In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent…
Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation
Shangding Gu, Bilgehan Sel, Yuhao Ding +4
Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications. Nevertheless, managing the trade-off between reward and safety during e…
TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning
Shangding Gu, Alois Knoll, Ming Jin
The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (R…