AI News HubLIVE
Original source2 min read

CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents

Proposes CORVUS, a novel trajectory architecture that decouples file-read actions from observations by maintaining a synchronized registry, significantly reducing redundant tokens and reasoning cycles for LLM coding agents while maintaining pass rates.

SourcearXiv Machine LearningAuthor: Mingwei Zheng, David OBrien, Siwei Cui, Pardis Pashakhanloo, Rajdeep Mukherjee, Myeongsoo Kim, Sachit Kuhar

-->

[Submitted on 20 Jul 2026]

Title:CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents

View a PDF of the paper titled CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents, by Mingwei Zheng and 6 other authors

View PDF

Abstract:LLM coding agents operate by constructing trajectories that accumulate reasoning, tool calls, and results to enable multi-step decision-making. However, the conventional append-only trajectory architecture found in practice tightly couples file-read actions with their observations, capturing snapshots that become permanently fixed in the chronological history. As files change through agent edits or concurrent human modifications, these snapshots become stale, causing reasoning errors and causing agents to redundantly re-read files, with each re-read appending yet another copy to the trajectory. To mitigate this, we propose CORVUS, a novel trajectory architecture that decouples file-read actions from their observations by maintaining a synchronized registry of relevant files and injecting only their current contents at each reasoning cycle. This structural change produces significantly lighter-weight trajectories that remain synchronized with the actual codebase state by construction, eliminating redundant file copies and stale snapshots that bloat conventional trajectories. We evaluated CORVUS on SWE- POLYBENCH_VERIFIED and SWE-BENCH PRO across four LLMs, achieving 9-50% reduction in average input tokens per task, 15-32% shorter final prompts, and up to 37% fewer reasoning cycles while maintaining comparable pass rates.

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Software Engineering (cs.SE)

Cite as: arXiv:2607.22711 [cs.LG]

(or arXiv:2607.22711v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2607.22711

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: David OBrien [view email] [v1] Mon, 20 Jul 2026 23:01:39 UTC (452 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents, by Mingwei Zheng and 6 other authors

View PDF

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-07

Change to browse by:

cs cs.AI cs.SE

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

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, Media

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

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

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.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)