# Evaluating Budgeted Context Projection with Unexecuted Companion Runs

arXiv: https://arxiv.org/abs/2609.31381 · HTML: https://mlsanity.com/paper/2609.31381/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [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)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models](https://mlsanity.com/paper/2310.05736/) (2023)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [ACON: Optimizing Context Compression for Long-horizon LLM Agents](https://mlsanity.com/paper/2510.00615/) (2025)
- [Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering](https://mlsanity.com/paper/2304.12102/) (2023)
- [The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management](https://mlsanity.com/paper/2508.21433/) (2025)
- [Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability](https://mlsanity.com/paper/2608.06503/) (2026)
- [SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness](https://mlsanity.com/paper/2609.20519/) (2026)
- [Token Reduction Is Not Cost Reduction](https://mlsanity.com/paper/2607.12161/) (2026)

## Abstract (arXiv)

Context projection can shorten individual requests while changing whether an agent finishes within its budget. We examine how sequential evaluation obscures this trade-off when a capped first continuation prevents its companion from running. In a recorded ReVerPi source-reading campaign, 15 pairs with two final answers yield 12 historically scored successes per arm. Retaining all 27 intervention boundaries distinguishes observed failures from ten unexecuted companions and bounds projected-minus-full success between -9 and +1 tasks. Under the archived scoring contract, a frozen projection selector has a success difference from full context of [-3,0]; outside four fitting tasks, it is [-4,-1] across 23 boundaries. Excluding one task whose platform premise is not established by retained actor-input evidence changes the nonfitting range to [-3,0] across 22 boundaries, so strict inferiority is not robust to that exclusion. Among eleven historically joint-success pairs, projection uses 25% fewer aggregate logical tokens but more tokens for the median pair and 55 rather than 35 suffix requests. These retrospective results concern one adaptively assembled campaign, not population performance. The case motivates accounting that retains every boundary, preserves unknown outcomes and policy dependencies, checks task premises, and separates bounded completion from success-conditioned resource use.