An Empirical Cost Attribution of Context-Compression Gateways in Multi-Turn Coding Agents
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Computation and Language
arXiv:2609.22114 (cs)
[Submitted on 19 Aug 2026]
Title:An Empirical Cost Attribution of Context-Compression Gateways in Multi-Turn Coding Agents
View a PDF of the paper titled An Empirical Cost Attribution of Context-Compression Gateways in Multi-Turn Coding Agents, by Luzhuo Chen and 1 other authors
View PDF
HTML (experimental)
Abstract:Context compression is widely proposed as a way to cut the token bill of LLM coding agents, and public benchmarks report that aggressive compression preserves task-solving quality. These two facts do not imply the third one commonly assumed: that compressing file reads saves money in a real multi-turn agent. We instrument a production compression gateway (Paritok) between coding agents (Claude Code, Codex) and frontier LLMs (Claude Sonnet, GPT-5), and decompose the token bill of real sessions into three independent levers: tool-schema filtering, content compression of file reads and tool output, and history summarization. Measured in isolation under controlled A/B runs, the three save at fundamentally different rates. Tool-schema filtering removes a fixed block every turn, roughly 21K-57K tokens on a typical turn; it is linear in the turn count N and the only unambiguously and reproducibly positive lever. Content compression saves only about 2% of the cache-priced prefix per turn, but compressed reads accumulate in history and are re-sent on every later turn, so its cumulative saving grows quadratically, about 3350*N^2 tokens (measured), overtaking the fixed tool-filter saving within roughly 6 turns until the context window caps it. A non-destructive gateway lets the agent pull original bytes back on demand; each recall re-sends exactly the one segment just compressed away, so its cost is fixed and bounded rather than a multiplicative blowup, and heavy recall spends the accumulated saving back one segment at a time. Finally, a strong single-shot compression benchmark - 86.5% of SWE-bench quality retained at a 25.7% compression rate, achieved by the model this gateway deploys (Paritok-4B, reported separately) - is orthogonal to multi-turn agent cost and must not be cited as a cost-saving argument. We distill the results into an actionable recipe for where token-saving effort pays off.
| Comments: | 10 pages, 1 figure, 4 tables |
| Subjects: | Computation and Language (cs.CL); Performance (cs.PF); Software Engineering (cs.SE) |
| MSC classes: | Primary: cs.AI Cross-list: cs.SE, cs.PF, cs.CL |
| ACM classes: | C.4; I.2.7; D.2.8 |
| Cite as: | arXiv:2609.22114 [cs.CL] |
| (or arXiv:2609.22114v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.22114
arXiv-issued DOI via DataCite
|
Full-text links:
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
View a PDF of the paper titled An Empirical Cost Attribution of Context-Compression Gateways in Multi-Turn Coding Agents, by Luzhuo Chen and 1 other authors
Current browse context:
cs.CL
References & Citations
Loading...
Bookmark
Bibliographic Tools
Code, Data, Media
Demos
Related Papers
About arXivLabs
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.