Cover Image

The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lindenbauer, Tobias, Slinko, Igor, Felder, Ludwig, Bogomolov, Egor, Zharov, Yaroslav
Format:	Preprint
Published:	2025
Subjects:	Software Engineering Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

GitGoodBench: A Novel Benchmark For Evaluating Agentic Performance On Git
by: Lindenbauer, Tobias, et al.
Published: (2025)

Step Rejection Fine-Tuning: A Practical Distillation Recipe
by: Slinko, Igor, et al.
Published: (2026)

On Problems of Implicit Context Compression for Software Engineering Agents
by: Gelvan, Kirill, et al.
Published: (2026)

PIPer: On-Device Environment Setup via Online Reinforcement Learning
by: Kovrigin, Alexander, et al.
Published: (2025)

Drawing Pandas: A Benchmark for LLMs in Generating Plotting Code
by: Galimzyanov, Timur, et al.
Published: (2024)

Tool-Augmented LLMs as a Universal Interface for IDEs
by: Zharov, Yaroslav, et al.
Published: (2024)

On The Importance of Reasoning for Context Retrieval in Repository-Level Code Editing
by: Kovrigin, Alexander, et al.
Published: (2024)

Challenge on Optimization of Context Collection for Code Completion
by: Ustalov, Dmitry, et al.
Published: (2025)

From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering Agents
by: Lindenbauer, Tobias, et al.
Published: (2025)

EnvBench: A Benchmark for Automated Environment Setup
by: Eliseeva, Aleksandra, et al.
Published: (2025)

Dynamic Retrieval-Augmented Generation
by: Shapkin, Anton, et al.
Published: (2023)

TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEs
by: Cipollone, Daniele, et al.
Published: (2025)

Multi-Agent Coordinated Rename Refactoring
by: Bellur, Abhiram, et al.
Published: (2026)

Long Code Arena: a Set of Benchmarks for Long-Context Code Models
by: Bogomolov, Egor, et al.
Published: (2024)

Stack Trace Deduplication: Faster, More Accurately, and in More Realistic Scenarios
by: Shibaev, Egor, et al.
Published: (2024)

Adoption of Generative Artificial Intelligence in the German Software Engineering Industry: An Empirical Study
by: Felder, Ludwig, et al.
Published: (2026)

LoCoBench-Agent: An Interactive Benchmark for LLM Agents in Long-Context Software Engineering
by: Qiu, Jielin, et al.
Published: (2025)

FlowMind: Execute-Summarize for Structured Workflow Generation from LLM Reasoning
by: Liu, Yihao, et al.
Published: (2026)

Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representation
by: Zhang, Lingzhe, et al.
Published: (2026)

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
by: Li, Yuanyang, et al.
Published: (2026)

Untangling Knots: Leveraging LLM for Error Resolution in Computational Notebooks
by: Grotov, Konstantin, et al.
Published: (2024)

CASET: Complexity Analysis using Simple Execution Traces for CS* submissions
by: Mehta, Aaryen, et al.
Published: (2024)

Leveraging LLMs, IDEs, and Semantic Embeddings for Automated Move Method Refactoring
by: Bellur, Abhiram, et al.
Published: (2025)

Graph-Based Self-Healing Tool Routing for Cost-Efficient LLM Agents
by: Bholani, Neeraj
Published: (2026)

Diff-XYZ: A Benchmark for Evaluating Diff Understanding
by: Glukhov, Evgeniy, et al.
Published: (2025)

LLM-Augmented Release Intelligence: Automated Change Summarization and Impact Analysis in Cloud-Native CI/CD Pipelines
by: Bhati, Happy
Published: (2026)

MicLog: Towards Accurate and Efficient LLM-based Log Parsing via Progressive Meta In-Context Learning
by: Yu, Jianbo, et al.
Published: (2026)

Rover: Context-aware Conflict Resolution with LLM
by: Zhang, Qingyu, et al.
Published: (2026)

Analysis on LLMs Performance for Code Summarization
by: Akib, Md. Ahnaf, et al.
Published: (2024)

Distilled GPT for Source Code Summarization
by: Su, Chia-Yi, et al.
Published: (2023)

RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
by: Bouzenia, Islem, et al.
Published: (2024)

MOSS: Enabling Code-Driven Evolution and Context Management for AI Agents
by: Zhu, Ming, et al.
Published: (2024)

On the Role of Fault Localization Context for LLM-Based Program Repair
by: Sepidband, Melika, et al.
Published: (2026)

Semantic Similarity Loss for Neural Source Code Summarization
by: Su, Chia-Yi, et al.
Published: (2023)

Meta-RAG on Large Codebases Using Code Summarization
by: Tawosi, Vali, et al.
Published: (2025)

SECite: Analyzing and Summarizing Citations in Software Engineering Literature
by: Pyreddy, Shireesh Reddy, et al.
Published: (2026)

Kotlin ML Pack: Technical Report
by: Titov, Sergey, et al.
Published: (2024)

Reducing Cost of LLM Agents with Trajectory Reduction
by: Xiao, Yuan-An, et al.
Published: (2025)

LLM Collaboration With Multi-Agent Reinforcement Learning
by: Liu, Shuo, et al.
Published: (2025)

Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling
by: Trae Research Team, et al.
Published: (2025)