Hugging Face Trending Papers
When Context Changes: Understanding Update Failures in LLMs
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv AI
3d ago
When Context Changes: Understanding Update Failures in LLMs
The paper introduces the concept of stale binding, where large language models (LLMs) answer with outdated values despite having newer information in context. It presents Controlled In-Context Memory (CICM), a benchmark to track and test the use of updated information in conversations and agent logs. Experiments on open‑source models reveal an attention drift mechanism that favors old values, and the authors propose a simple attention‑redirecting intervention that largely corrects these errors without harming correct answers.
arXiv AI
Sep 2
Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning
The paper introduces the Unified Memory Agent (UMA), a system that builds a query‑agnostic external memory from a data stream and reuses it across multiple question‑answering sessions. UMA employs a single policy to manage a structured Memory Bank via CRUD operations and uses Task‑Stratified GRPO to supervise memory maintenance based on QA trajectory rewards. The authors also present Ledger‑QA, a benchmark for long‑horizon state tracking, and demonstrate that UMA outperforms other methods on test‑time learning and accurate‑retrieval tasks, with UMA‑Specialist further improving performance after task adaptation.
arXiv AI
Jul 15
MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
arXiv:2607. 12893v1 Announce Type: new Abstract: Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions.
arXiv Machine Learning
Aug 4
LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference
arXiv:2608. 02515v1 Announce Type: cross Abstract: Long-running assistants and agents consume interaction streams that eventually outgrow the context.
arXiv Machine Learning
Jul 10
When Does Continual Learning Require Learning
arXiv:2607. 07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn?
arXiv Computation and Language
3d ago
Persistent Context Graphs for Efficient Memory Compaction in LLM Agents
arXiv:2609.40118v1 Announce Type: new Abstract: As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compa...