MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off Paper • 2608.04843 • Published Aug 5 • 3
The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads Paper • 2608.04570 • Published Aug 5 • 41
When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents Paper • 2608.04574 • Published Aug 5 • 16
Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants Paper • 2607.26611 • Published Jul 29 • 33
Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering Paper • 2603.28583 • Published Jul 14 • 10
Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists Paper • 2607.11079 • Published Jul 13 • 5
When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers Paper • 2607.00394 • Published Jul 1 • 5
Cross-domain-aware Worker Selection with Training for Crowdsourced Annotation Paper • 2406.06977 • Published Jun 11, 2024
Are Large Language Models a Good Replacement of Taxonomies? Paper • 2406.11131 • Published Jun 20, 2024
KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering Paper • 2509.04716 • Published Sep 5, 2025
LakeHopper: Cross Data Lakes Column Type Annotation through Model Adaptation Paper • 2602.08793 • Published Feb 9
GRAVITY: Architecture-Agnostic Structured Anchoring for Long-Horizon Conversational Memory Paper • 2605.01688 • Published May 3 • 2
APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL Paper • 2602.16720 • Published Feb 11 • 1
MedKGI: Iterative Differential Diagnosis with Medical Knowledge Graphs and Information-Guided Inquiring Paper • 2512.24181 • Published Dec 30, 2025
The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads Paper • 2608.04570 • Published Aug 5 • 41
The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads Paper • 2608.04570 • Published Aug 5 • 41
When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents Paper • 2608.04574 • Published Aug 5 • 16
When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents Paper • 2608.04574 • Published Aug 5 • 16
Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants Paper • 2607.26611 • Published Jul 29 • 33
Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants Paper • 2607.26611 • Published Jul 29 • 33