# LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception arXiv: https://arxiv.org/abs/2606.30005 ยท HTML: https://mlsanity.com/paper/2606.30005/ ## Key facts - Cited by 3 papers in the map (data through 14 Oct 2026). - Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. - Builds on 45 of its 55 references that are in the map. - First posted on arXiv 29 Jun 2026. ## Placed in - LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/) ## Builds on (most cited first, 30 of 45) - [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023) - [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023) - [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025) - [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025) - [SimpleMem: Efficient Lifelong Memory for LLM Agents](https://mlsanity.com/paper/2601.02553/) (2026) - [Scaling Long-Horizon LLM Agent via Context-Folding](https://mlsanity.com/paper/2510.11967/) (2025) - [ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization](https://mlsanity.com/paper/2509.13313/) (2025) - [ACON: Optimizing Context Compression for Long-horizon LLM Agents](https://mlsanity.com/paper/2510.00615/) (2025) - [HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model](https://mlsanity.com/paper/2408.09559/) (2024) - [Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents](https://mlsanity.com/paper/2601.01885/) (2026) - [Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering](https://mlsanity.com/paper/2604.08224/) (2026) - [Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2510.12635/) (2025) - [AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications](https://mlsanity.com/paper/2602.22769/) (2026) - [Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents](https://mlsanity.com/paper/2602.01869/) (2026) - [Context as a Tool: Context Management for Long-Horizon SWE-Agents](https://mlsanity.com/paper/2512.22087/) (2025) - [PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agents](https://mlsanity.com/paper/2603.03296/) (2026) - [MEMENTO: Teaching LLMs to Manage Their Own Context](https://mlsanity.com/paper/2604.09852/) (2026) - [Active Context Compression: Autonomous Memory Management in LLM Agents](https://mlsanity.com/paper/2601.07190/) (2026) - [One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP](https://mlsanity.com/paper/2505.19840/) (2025) - [Learning Agent-Compatible Context Management for Long-Horizon Tasks](https://mlsanity.com/paper/2605.30785/) (2026) - [LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth](https://mlsanity.com/paper/2602.07962/) (2026) - [ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents](https://mlsanity.com/paper/2604.01664/) (2026) - [Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory](https://mlsanity.com/paper/2602.06025/) (2026) - [Evidence for Limited Metacognition in LLMs](https://mlsanity.com/paper/2509.21545/) (2025) - [Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Search](https://mlsanity.com/paper/2510.18939/) (2025) - [Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL](https://mlsanity.com/paper/2602.03773/) (2026) - [Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory](https://mlsanity.com/paper/2603.04257/) (2026) - [CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation](https://mlsanity.com/paper/2507.05113/) (2025) - [From Samples to Scenarios: A New Paradigm for Probabilistic Forecasting](https://mlsanity.com/paper/2509.19975/) (2025) - [GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)](https://mlsanity.com/paper/2604.17091/) (2026) ## Built on by (most cited first, 3 of 3) - [An Empirical Study of Harness Design for Coding Agents](https://mlsanity.com/paper/2609.20804/) (2026) - [Memory Control Signals Emerge Before Action in Long Horizon Agents](https://mlsanity.com/paper/2609.27286/) (2026) - [Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers](https://mlsanity.com/paper/2609.01466/) (2026) ## Abstract (arXiv) Long-horizon tool agents are bottlenecked by how their context grows toward the limits of the context window. Recent systems make context management agent- or system-controlled, but they either learn compression policies that discard evidence or manage context in a layer the agent never sees. We argue that both miss a more basic gap: frontier language models are proprioceptively blind to their own context. From the prompt alone they cannot reliably infer block size, recency, or the remaining budget, all of which are needed for keep-or-archive decisions. We introduce VISTA (Visible Internal State for Tool Agents), a training-free, model-agnostic layer that represents working memory as typed addressable blocks, surfaces a runtime dashboard of token usage, recency, archive status, and remaining budget, and archives blocks as recoverable full-fidelity payloads. On LOCA-Bench, BrowseComp-Plus, and GAIA, the same untrained interface transfers across 1M-, 100K-, and 10K-scale trajectories. On LOCA-Bench it lifts Gemini-3-Flash from 22.7 to 50.7%, reaches 58.0% on BrowseComp-Plus, and remains competitive on GAIA. Gains grow with context pressure and transfer across backbones, while ablations confirm that the dashboard matters beyond archive and recovery tools.