LLM Digest

Story

arxiv_cs_lg · Nov 1, 2026 · paper

Source brief

Evolving Memory, Learning to Meta-Control: Test-Time Adaptation for Experience-augmented LLM Agents

arxiv.orgNov 1, 2026
original source linked

In brief

Self-evolving agents accumulate experience from task streams, but existing frameworks typically rely on fixed pipelines to retrieve and utilize this experience, neglecting when and how to deploy it. We introduce Onlin...

Feed lens

agenteval

Read the original at arxiv.org →Open in live feed Read that day’s brief

Evolving Memory, Learning to Meta-Control: Test-Time Adaptation for Experience-augmented LLM Agents

Earlier in this thread 4 items

METTA: Memory-Enhanced Test-Time Adaptation for Meta-Reinforcement Learning

Sparse MLLM Anchors, Dense Adaptation: Breaking the Self-Referential Loop in Wild Test-Time Adaptation

Lifelong Context Adaptation through Bidirectional Memory-Skill Learning

SWE-Shift: Evaluating Coding Agents in Evolving Workspaces