Skip to content
Review

Context Compression for LLM Agents: A Survey of Methods, Failure Modes, and Evaluation

Unknown authors
· 10 citations · 1 references

TL;DR

A unified taxonomy of agent context compression along three dimensions is introduced: compression target (what is compressed), compression mechanism (how it is transformed and retained), and control policy (who decides when compression is triggered).

View source

Similar papers

Preprint Aug 2026

Automata from Agent Traces: Failure and Next-Step Prediction

Behavioral topology is shaped more by the deployment harness than by the LLM, providing a model-agnostic structural primitive for safety auditing and runtime monitoring, and addresses both prediction goals.

Seonglae Cho, F. Fernandez, Umar Mohammed et al. · 3 citations
#machine learning Preprint Sep 2026

Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents

This paper proposes FRESH, a Failure-aware Retrieval framework over Experience-Structured Heterogeneous graphs, which transforms historical successes and failures into structured external experience for tool-using agents and consistently improves task success and tool-use reliability over no-memory agents and represent...

Jia-Xing Li, Lei Song, Rui Dong et al. · 0 citations
#natural language process... Preprint Sep 2026

Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement

Dynamic Retrieval-based Policy Generation (DRPG) is proposed, a framework that integrates memory-based retrieval with a dynamic policy generator, leveraging historical data and environment feedback to produce task-specific policies for continual LLM improvement.

Ting-Wei Chang, Po-Chun Chen, Hen-Hsen Huang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.