arXiv (All)
open access
MemoryWalker: Stop Training Agents on Contexts They Never Saw
Production agent harnesses such as Claude Code and Qwen-Agent compress context during rollout, but training under compression creates a conditioning problem: every eviction branches the effective history, so the learning object is a tree rather than a sequence. Existing linearizations either retain
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Hindsight Memory-PRM: Supervising Memory Management with Auditable Hindsight Credit#798245
- Hindsight Memory-PRM: Supervising Memory Management with Auditable Hindsight Credit#796832
- Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning#1144440
- Preservationism in the Epistemology of Memory#735069
- Pseudo-visibility: A Game Mechanic Involving Willful Ignorance#104906
Record · ID 820867
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive