Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
Paper • 2605.26302 • Published • 32
AI & ML interests
Trustworthy Machine Learning and Reasoning
Papers
AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
ZfancyÂ
submitted a
paper to Daily Papers 3 months ago
ZfancyÂ
authored 12
papers 3 months ago
Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability
Paper • 2306.03715 • Published
Exploring Model Dynamics for Accumulative Poisoning Discovery
Paper • 2306.03726 • Published
Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?
Paper • 2410.23856 • Published • 5
DeepInception: Hypnotize Large Language Model to Be Jailbreaker
Paper • 2311.03191 • Published • 2
Co-Reward: Self-supervised Reinforcement Learning for Large Language Model Reasoning via Contrastive Agreement
Paper • 2508.00410 • Published • 1
What If the Input is Expanded in OOD Detection?
Paper • 2410.18472 • Published
AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
Paper • 2605.08715 • Published • 8
Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
Paper • 2406.09179 • Published
Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts
Paper • 2605.09296 • Published • 5
Belief Memory: Agent Memory Under Partial Observability
Paper • 2605.05583 • Published • 2
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
Paper • 2605.19952 • Published • 9
Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
Paper • 2605.26302 • Published • 32
SuperjwÂ
authored a
paper 3 months ago
SuperjwÂ
submitted 2
papers to Daily Papers 3 months ago
SuperjwÂ
authored a
paper 3 months ago
AboriginerÂ
authored 3
papers 5 months ago
AlphaApollo: Orchestrating Foundation Models and Professional Tools into a Self-Evolving System for Deep Agentic Reasoning
Paper • 2510.06261 • Published • 6
Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
Paper • 2509.11629 • Published • 1
Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
Paper • 2406.00806 • Published