# Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents

arXiv: https://arxiv.org/abs/2605.08580 · HTML: https://mlsanity.com/paper/2605.08580/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 9 May 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 30)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization](https://mlsanity.com/paper/2005.03754/) (2020)
- [QuestEval: Summarization Asks for Fact-based Evaluation](https://mlsanity.com/paper/2103.12693/) (2021)
- [An LLM Compiler for Parallel Function Calling](https://mlsanity.com/paper/2312.04511/) (2023)
- [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)
- [Context Length Alone Hurts LLM Performance Despite Perfect Retrieval](https://mlsanity.com/paper/2510.05381/) (2025)
- [FABLES: Evaluating faithfulness and content selection in book-length summarization](https://mlsanity.com/paper/2404.01261/) (2024)
- [SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning](https://mlsanity.com/paper/2504.07891/) (2025)
- [Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management](https://mlsanity.com/paper/2510.06727/) (2025)
- [RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression](https://mlsanity.com/paper/2502.14051/) (2025)
- [Re-Examining System-Level Correlations of Automatic Summarization Evaluation Metrics](https://mlsanity.com/paper/2204.10216/) (2022)
- [Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization](https://mlsanity.com/paper/2209.03549/) (2022)
- [Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference](https://mlsanity.com/paper/2509.09505/) (2025)

## Built on by (most cited first, 6 of 6)

- [Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents](https://mlsanity.com/paper/2606.22528/) (2026)
- [The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents](https://mlsanity.com/paper/2608.06663/) (2026)
- [Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers](https://mlsanity.com/paper/2609.01466/) (2026)
- [LAM: Efficient Lossy Agent Memory Framework With A Retrieval-Score Error Bound](https://mlsanity.com/paper/2609.32256/) (2026)
- [StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents](https://mlsanity.com/paper/2609.36319/) (2026)
- [Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents](https://mlsanity.com/paper/2610.18784/) (2026)

## Abstract (arXiv)

To cope with the large contexts that long-horizon LLM agents produce, modern frameworks increasingly rely on compaction -- invoking an LLM to rewrite the accumulated trajectory into a shorter summary that the agent resumes from. Today, compaction runs synchronously on the critical path of agent execution but this can unpredictably degrade accuracy due to a structural validation gap: the compactor must condense context but is fundamentally unaware of precisely what information the agent will need later. Further, because post-compaction agent steps are conditioned on the new summary, targeted validation criteria do not exist and errors silently propagate through coherent but incorrect behavior. Our key insight is that asynchronous compaction efficiently addresses this gap: by running the compactor in parallel with continued agent execution on the original context, the candidate summary and the agent's next steps are generated independently from the same pre-compaction state, yielding a validation signal independent of the summary itself. We build Slipstream, a trajectory-grounded compaction system that uses a judge to validate the candidate summary against the agent's continued reasoning, checking that it preserves both the agent's forward intent and the key facts and constraints it depends on. Across long-horizon coding (SWE-bench Verified) and web-browsing (BrowseComp) workloads, Slipstream improves task accuracy by up to 8.8 percentage points while reducing end-to-end latency by up to 39.7%.