arXiv (All)
open access
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been the most popular mechanism to alleviate this issue, keeping GPU memory constant for a given trace. Unfortunately, most compaction strategies rely on prefilling
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
- KV-streams for Efficient Compaction in Agentic Reinforcement Learning#1108745
- Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training#423982
- S3C-LLM: Skill-Code Guided Agentic Language Models for Spectrum-to-Structure Elucidation#622536
- CoMem: Collective-Individual Memory Synergy for Evolutionary Multi-Agent Systems#1084908
- Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games#144303
Record · ID 1141649
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