CF
Charles Fleming
cs.AIcs.LGcs.CLcs.CRstat.MEcs.CVcs.DCcs.ETcs.MAcs.RO
On Valency
published · living versionsW_5m5qrfhy·v1 · currentpublished
Know When to Escalate: Critic-Guided Adaptive Execution for Cloud-Local Embodied Agents
with Wei Zhang, Lirong Xiang
1 version
W_hb7ygqfd·v1published
Preprints & journals
17 papers in the corpus · 2025–2026Know When to Escalate: Critic-Guided Adaptive Execution for Cloud-Local Embodied Agents2610.30587v1 · Wei Zhang, Lirong Xiang, Charles Fleming2026 · 0 citationsarXivon Valency
Combating Catastrophic Forgetting in Continual Domain Adaptation via Knowledge Recasting2610.28892v1 · Zijie Liu, Zhen Tan, Charles Fleming et al.2026 · 0 citationsarXivon Valency
VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning2610.10782v1 · Meng Lu, Ligeng Zhu, Olivia Xiao et al.2026 · 0 citationsarXiv
MASkills: Continual Skills Optimization for Multi-Agent LLM Systems2609.02094v1 · Huaiyuan Yao, Xiaoou Liu, Charles Fleming et al.2026 · 0 citationsEMNLP 2026 Findings
REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces2606.09071v1 · Xiaofeng Lin, Yingxu Wang, Tung Sum Thomas Kwok et al.2026 · 0 citationsarXiv
Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps2606.09084v1 · Xiaofeng Lin, Yukai Yang, Daniel Guo et al.2026 · 0 citationsarXiv
Cordyceps: Covert Control Attacks on LLMs via Data Poisoning2605.26595v2 · Zedian Shao, Charles Fleming, Teodora Baluta2026 · 0 citationsarXiv
Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory2605.03228v2 · Yuhui Wang, Tanqiu Jiang, Jiacheng Liang et al.2026 · 0 citationsarXiv
LangMARL: Natural Language Multi-Agent Reinforcement Learning2604.00722v1 · Huaiyuan Yao, Longchao Da, Xiaoou Liu et al.2026 · 0 citationsarXiv
Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory2604.01007v2 · Jiaqi Liu, Zipeng Ling, Shi Qiu et al.2026 · 0 citationsarXiv
AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science2603.19005v3 · An Luo, Jin Du, Xun Xian et al.2026 · 0 citationsarXiv
ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement Learning2603.10823v2 · Xiaofeng Lin, Seungbae Kim, Zhuoya Li et al.2026 · 0 citationsarXiv
TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT2602.03073v1 · Rana Muhammad Shahroz Khan, Zijie Liu, Zhen Tan et al.2026 · 0 citationsarXiv
Window-based Membership Inference Attacks Against Fine-tuned Large Language Models2601.02751v2 · Yuetian Chen, Yuntao Du, Kaiyuan Zhang et al.2026 · 0 citationsarXiv
Can Agentic AI Match the Performance of Human Data Scientists?2512.20959v1 · An Luo, Jin Du, Fangqiao Tian et al.2025 · 0 citationsarXiv
Probing Knowledge Holes in Unlearned LLMs2511.00030v1 · Myeongseob Ko, Hoang Anh Just, Charles Fleming et al.2025 · 0 citationsarXiv
An Outlook on the Opportunities and Challenges of Multi-Agent AI Systems2505.18397v3 · Fangqiao Tian, An Luo, Jin Du et al.2025 · 0 citationsarXiv
Career total: 18 works. 17 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.