MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off
Paper • 2608.04843 • Published • 3
Yushi SUN
Yushi98
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 months ago
MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off authored a paper about 2 months ago
The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads authored a paper about 2 months ago
When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM AgentsOrganizations
None yet
upvoted 4
papers about 2 months ago
The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads
Paper • 2608.04570 • Published • 41
When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents
Paper • 2608.04574 • Published • 16
Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants
Paper • 2607.26611 • Published • 33
upvoted 3
papers 3 months ago
Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists
Paper • 2607.11079 • Published • 5
Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering
Paper • 2603.28583 • Published • 10
When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers
Paper • 2607.00394 • Published • 5
upvoted 3
papers 5 months ago
GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory
Paper • 2605.01688 • Published • 2
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
Paper • 2605.06527 • Published • 48
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
Paper • 2605.13831 • Published • 90