[2606.20047] PACMS: Submodular Context Selection as a Pluggable Engine for LLM Agents

-->

Computer Science > Information Retrieval

arXiv:2606.20047 (cs)

[Submitted on 18 Jun 2026]

Title:PACMS: Submodular Context Selection as a Pluggable Engine for LLM Agents

Authors:Manu Ghulyani, Arunabh Singh, Karan Bharadwaj, Ankit Nath, Suranjan Goswami<br>View a PDF of the paper titled PACMS: Submodular Context Selection as a Pluggable Engine for LLM Agents, by Manu Ghulyani and 3 other authors

View PDF<br>HTML (experimental)

Abstract:Conversational and tool-using LLM agents operate over a context window that fills from several directions simultaneously. As a session proceeds, the agent accumulates user and assistant turns, entries drawn from a persistent memory store, and often largest of all, the verbatim outputs of tool calls such as file reads, search results, and API responses. Once the cumulative context exceeds the model's token budget, the framework must decide what to keep.

The prevailing mechanism is recency truncation, sometimes paired with periodic summarization. This is topic-blind: a fact established early in a session is discarded simply because it is old, even when the current user query is about exactly that fact; conversely, verbose but irrelevant recent material is retained. Agents that must recall information across many turns, the defining case for memory, are precisely where recency truncation fails.

Existing alternatives sit outside the agent's assembly step. Retrieval augmented generation fetches external documents into the prompt but does not arbitrate the agent's \emph{already-present} pooled context. Context-compression methods reduce token count by rewriting or pruning text, but operate query-blind and lossily. Neither treats memory entries, conversation turns, and tool outputs as a single candidate pool to be selected from by relevance at the moment the prompt is assembled.

Subjects:

Information Retrieval (cs.IR)

Cite as:<br>arXiv:2606.20047 [cs.IR]

(or<br>arXiv:2606.20047v1 [cs.IR] for this version)

https://doi.org/10.48550/arXiv.2606.20047

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Suranjan Goswami [view email]<br>[v1]<br>Thu, 18 Jun 2026 10:22:57 UTC (90 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled PACMS: Submodular Context Selection as a Pluggable Engine for LLM Agents, by Manu Ghulyani and 3 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.IR

next >

new<br>recent<br>| 2026-06

Change to browse by:

cs

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

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?)

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? |<br>Disable MathJax (What is MathJax?)