works on

From the 1 of 11 linked papers with an AI index.

collaborators

11 papers

cs.CL2026

LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception

Binyan Xu, Haitao Li, Kehuan Zhang

The paper demonstrates that large language model agents can better manage their working memory when given an interface that reveals the size, age, and usage of each memory block, i…

cs.AI2026

When Agent Automation Becomes Profitable: Quantifying and Insuring Autonomous AI Risk through Trace-Economic Underwriting

Binyan Xu, Xilin Dai, Fan Yang +1

AI agents can now take irreversible actions in operational systems, but agent-caused losses are still not clearly assigned, priced, or transferred. Providers often disclaim consequ…

cs.LG2026

From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor Defense

Binyan Xu, Fan Yang, Xilin Dai +2

Deep Neural Networks remain inherently vulnerable to backdoor attacks. Traditional test-time defenses largely operate under the paradigm of internal diagnosis methods like model re…

cs.LG2026

Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors

Fan Yang, Binyan Xu, Di Tang +1

GNNs have become a standard tool for learning on relational data, yet they remain highly vulnerable to backdoor attacks. Prior defenses often depend on inspecting specific subgraph…

cs.DL2026

Reviewer Scores Are Not Comparable Across Research Areas in ML Peer Review

Binyan Xu, Fan Yang, Xilin Dai +1

Peer review at ML conferences increasingly relies on reviewer scores as the primary decision instrument. As submissions have scaled from thousands to tens of thousands per year, no…

cs.AI2026

Contextual Agentic Memory is a Memo, Not True Memory

Binyan Xu, Xilin Dai, Kehuan Zhang

Current agentic memory systems (vector stores, retrieval-augmented generation, scratchpads, and context-window management) do not implement memory: they implement lookup. We argue…