STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
Paper • 2605.06527 • Published • 37 •
2
Librarian Bot (Bot)
librarian-bot
AI & ML interests
I am a friendly librarian bot working to help improve metadata on the 🤗 hub. Run by Hugging Face'ss Machine Learning Librarian (HF username: davanstrien)
Recent Activity
commentedon a paper about 14 hours ago
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid? commentedon a paper about 14 hours ago
WildTableBench: Benchmarking Multimodal Foundation Models on Table Understanding In the Wild commentedon a paper about 14 hours ago
RouteProfile: Elucidating the Design Space of LLM Profiles for RoutingOrganizations
commented 5
papers about 14 hours ago
WildTableBench: Benchmarking Multimodal Foundation Models on Table Understanding In the Wild
Paper • 2605.01018 • Published • 6 •
2
RouteProfile: Elucidating the Design Space of LLM Profiles for Routing
Paper • 2605.00180 • Published • 27 •
2
Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding
Paper • 2605.07637 • Published • 16 •
3
Long Context Pre-Training with Lighthouse Attention
Paper • 2605.06554 • Published • 18 •
2
Librarian Bot: Add language metadata for dataset
#2 opened 1 day ago
by librarian-bot
commented 6
papers 1 day ago
Federation of Experts: Communication Efficient Distributed Inference for Large Language Models
Paper • 2605.06206 • Published • 1 •
2
Retrieval from Within: An Intrinsic Capability of Attention-Based Models
Paper • 2605.05806 • Published • 5 •
2
KL for a KL: On-Policy Distillation with Control Variate Baseline
Paper • 2605.07865 • Published • 17 •
3
AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents
Paper • 2605.06607 • Published • 1 •
2
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
Paper • 2605.05704 • Published • 1 •
2
FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation
Paper • 2605.04651 • Published • 1 •
2
Librarian Bot: Add language metadata for dataset
#2 opened 2 days ago
by librarian-bot
commented 7
papers 3 days ago
SEIF: Self-Evolving Reinforcement Learning for Instruction Following
Paper • 2605.07465 • Published • 28 •
2
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
Paper • 2605.07579 • Published • 15 •
3
World Model for Robot Learning: A Comprehensive Survey
Paper • 2605.00080 • Published • 16 •
2
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
Paper • 2605.05630 • Published • 11 •
2
Relit-LiVE: Relight Video by Jointly Learning Environment Video
Paper • 2605.06658 • Published • 15 •
2
Implicit Preference Alignment for Human Image Animation
Paper • 2605.07545 • Published • 1 •
2
Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs
Paper • 2605.07153 • Published • 6 •
2