arXiv (All)
open access
Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations
Long-horizon agents require context compression to manage growing interaction histories. Compression quality, however, is ultimately determined by downstream execution. Existing prompt-adaptation methods infer compression errors by comparing full-context and compressed trajectories. Such comparisons
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
- StateFlow: Sequence Pipeline Parallelism for Long-Context Modeling with Linear Recurrence#440341
- GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning#229439
- StepKV: Step-Aware KV Cache Compression for LLM Agents#1036841
- A Comprehensive Study of Content Representations for Speech Synthesis#1105534
- GWT: Scalable Optimizer State Compression for Large Language Model Training#670313
Record · ID 1131727
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