Trained Agentic Context Management
On the map: LLM agents and tool use → Agent memory systems also fits: General LLM agent frameworks and benchmarks
Abstract (arXiv)
We study long context language models. Instead of training long context natively, or designing a long context harness, we train a model over the simplest possible harness: a tool to call itself with any specified prompt and a tool to read tokens in a range from the input context. We finetune Qwen3.6-35B-A3B on a diverse synthetic dataset using this harness. With only 8,000 tokens of context, our small model is as strong as GPT-5.4 with 1M tokens of context on the OOLONG-synth benchmark when document length exceeds 40K tokens.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. First posted on arXiv 1 Oct 2026.
Builds on
No reference list yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Bootstrap Your Own Context Length
- 2025Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation
- 2026ContextPipe: Database-Inspired Context Assembly for Long-Horizon Agents
- 2025LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions
- 2024LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
- 2025ACON: Optimizing Context Compression for Long-horizon LLM Agents
- 2026LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception
- 2025A Survey of Context Engineering for Large Language Models