---
title: "Semantic Context Handoff with On-Demand... | SI Paper Desk"
url: https://thesimind.si/papers/2611.24357/
description: "SCH keeps a short summary of what an SI agent currently thinks, stores the raw evidence separately, and brings old evidence back when needed. This improved..."
---

Number 8 of 12 · November 20, 2026

# Semantic Context Handoff with On-Demand Evidence for Long-Horizon Agents

SCH keeps a short summary of what an SI agent currently thinks, stores the raw evidence separately, and brings old evidence back when needed. This improved results and cut cost.

Guolong Zheng, Chen Hou, Xu Yang and 2 more · Submitted November 18, 2026 · arXiv 2611.24357v1 · cs.AI

[Read the paper on arXiv](https://arxiv.org/abs/2611.24357) · [The PDF](https://arxiv.org/pdf/2611.24357) · [The day's 12](https://thesimind.si/papers/day/2026-11-20/)

## What they found

The authors propose Semantic Context Handoff (SCH) for SI agents that work on long tasks. A short "semantic state" holds the agent's current interpretation. The earlier actions and observations stay stored on the side and can return to context when they become relevant. This needs no separate summarizing or retrieval-model calls. In a controlled 150-task SWE-bench study, bringing evidence back raised Pass@1 from 80.0% to 86.9% at essentially unchanged token use and time. Against the strongest baseline by task performance, SCH reached 86.9% Pass@1 with 43% fewer tokens and 41% less wall-clock time. Across models and benchmarks, it used fewer tokens than full-history prompting and stayed competitive with or beat the evaluated baselines. The authors' trajectory analysis says SCH recovers evidence from much earlier in the history, not just from recent context.

## Why it matters

Long-running SI agents usually keep every past step in their prompt. That gets costly and may hurt accuracy. Methods that drop old observations save cost but can lose facts that matter later. This paper tries to keep the savings without that loss. The abstract does not say which baselines or benchmarks beyond SWE-bench were used, so the wider claims are hard to judge from it.

## How it changes the race

If the results hold, teams building agents could run longer tasks at lower cost and with better accuracy, without extra models for summarizing or retrieval. This is a gain in how context is managed, not a new SI model.

### The abstract, by the authors

Traditional long-horizon LLM agents often hand off context through full-history prompting, retaining all previous action-observation interactions. As execution proceeds, this history keeps growing, increasing inference cost and potentially degrading accuracy. Existing methods control this growth by preserving compact conclusions while removing earlier observations, but doing so can discard evidence that later becomes relevant. We introduce Semantic Context Handoff (SCH), whose central abstraction is state-evidence separation: a compact semantic state carries the agent's current interpretation, while supporting action-observation evidence remains separately addressable and can re-enter context when later execution makes it relevant, without separate summarization or retrieval-model calls. Empirically, SCH improves long-horizon agent performance while substantially reducing context cost. In a controlled 150-task SWE-bench study, SCH's evidence recovery improves Pass@1 from 80.0% to 86.9% at essentially unchanged token use and execution time. In the complete-system comparison, SCH achieves 86.9% Pass@1 while using 43% fewer tokens and 41% less wall-clock time than the strongest baseline by task performance. Across models and benchmarks, SCH consistently reduces token use relative to full-history prompting while remaining competitive with or improving upon the evaluated baselines. Trajectory analysis confirms that SCH recovers evidence from substantially earlier parts of the interaction history rather than merely preserving a recent context window.

Quoted from arXiv:2611.24357. The research and its words belong to its authors.

Desk score **78** out of 100

Why it was picked

- Agents (in the title)
- Reasoning (in the title)
- Compute
- Evals
- Language models

Topics

- [Agents](https://thesimind.si/papers/?tag=agents)
- [Memory](https://thesimind.si/papers/?tag=memory)
- [Efficiency](https://thesimind.si/papers/?tag=efficiency)
- [Code](https://thesimind.si/papers/?tag=code)
- [Benchmarks](https://thesimind.si/papers/?tag=benchmarks)
- [Language models](https://thesimind.si/papers/?tag=language-models)

**arXiv ID:** 2611.24357v1
**Submitted:** November 18, 2026
**Fields:** cs.AI (Artificial Intelligence)
**Level:** Intermediate

Fingerprint, SHA-256

`fa166152132ed51aadebfdbf7691a9851e855283c6c506abd66b32a18bae634b`

On Solana: [Proof of Mind seal, 4JtzxB...6w5n](https://solscan.io/tx/4JtzxBBunUdHpdT7ydTygvUny81ph9bmXUMt9UHMJBLFrSwBZFdTbtV5CcZdHAM2kg7Bc2pTnq59P4DvXyGc6w5n)

### The exact text fingerprinted

{"arxiv":"2611.24357","version":1,"title":"Semantic Context Handoff with On-Demand Evidence for Long-Horizon Agents","authors":["Guolong Zheng","Chen Hou","Xu Yang","Jianshan Zhang","Tao Huang"],"day":"2026-11-20","rank":8,"score":78,"status":"written","summary":{"takeaway":"SCH keeps a short summary of what an SI agent currently thinks, stores the raw evidence separately, and brings old evidence back when needed. This improved results and cut cost.","found":"The authors propose Semantic Context Handoff (SCH) for SI agents that work on long tasks. A short \"semantic state\" holds the agent's current interpretation. The earlier actions and observations stay stored on the side and can return to context when they become relevant. This needs no separate summarizing or retrieval-model calls. In a controlled 150-task SWE-bench study, bringing evidence back raised Pass@1 from 80.0% to 86.9% at essentially unchanged token use and time. Against the strongest baseline by task performance, SCH reached 86.9% Pass@1 with 43% fewer tokens and 41% less wall-clock time. Across models and benchmarks, it used fewer tokens than full-history prompting and stayed competitive with or beat the evaluated baselines. The authors' trajectory analysis says SCH recovers evidence from much earlier in the history, not just from recent context.","matters":"Long-running SI agents usually keep every past step in their prompt. That gets costly and may hurt accuracy. Methods that drop old observations save cost but can lose facts that matter later. This paper tries to keep the savings without that loss. The abstract does not say which baselines or benchmarks beyond SWE-bench were used, so the wider claims are hard to judge from it.","race":"If the results hold, teams building agents could run longer tasks at lower cost and with better accuracy, without extra models for summarizing or retrieval. This is a gain in how context is managed, not a new SI model.","safety":"","level":"intermediate","tags":["agents","memory","efficiency","code","benchmarks","language-models"]}}

[Check it on Verify a thought](https://thesimind.si/proof-of-mind/)

## The authors

Guolong Zheng, Chen Hou, Xu Yang, Jianshan Zhang, Tao Huang

Credit for this research belongs to its authors. SI MIND's page is a plain-English reading of their abstract on arXiv, not a review of the full paper.

Related on the desk

## More papers on these topics

[Nov 10, 2026 · Number 3PACE: Keeping the Right Tokens in the KV Cache Is Not Enough for Long-Horizon LLM AgentsKeeping the needed tokens in a SI agent's memory cache is not enough. PACE also renumbers their positions so they stay reachable, and it holds accuracy in sessions of up to 2M tokens.AgentsEfficiencyMemory](https://thesimind.si/papers/2611.10240/) · [Nov 12, 2026 · Number 2AgentScript-Eval: Benchmarking LLMs and Agents for Code Generation in an Enterprise DSLOn a new benchmark for a private Salesforce agent language, SI models mostly fail zero-shot, and the setup around the model, like a compile-and-edit loop and clear guidance, mattered more than model size.BenchmarksCodeAgents](https://thesimind.si/papers/2611.13183/) · [Nov 11, 2026 · Number 10AMSchem: Automated Schematic Visualization of AMS Circuits via Verifiable Agentic GenerationAMSchem uses an SI agent with strict automatic checks to turn analog circuit netlists into readable schematics, reaching 85.0% validity versus 32.5% for direct generation on a 40-circuit subset.AgentsCodeEvals](https://thesimind.si/papers/2611.12333/)

[Number 7](https://thesimind.si/papers/2611.24362/) · [All 12 for Nov 20, 2026](https://thesimind.si/papers/day/2026-11-20/) · [Number 9](https://thesimind.si/papers/2611.23388/)
