# Reducing Cost of LLM Agents with Trajectory Reduction

arXiv: https://arxiv.org/abs/2509.23586 · HTML: https://mlsanity.com/paper/2509.23586/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 36 of its 50 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents](https://mlsanity.com/paper/2506.15841/) (2025)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [Compressing Context to Enhance Inference Efficiency of Large Language Models](https://mlsanity.com/paper/2310.06201/) (2023)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving](https://mlsanity.com/paper/2504.02605/) (2025)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference](https://mlsanity.com/paper/2403.09636/) (2024)
- [Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling](https://mlsanity.com/paper/2507.23370/) (2025)
- [Learning to Filter Context for Retrieval-Augmented Generation](https://mlsanity.com/paper/2311.08377/) (2023)
- [Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)](https://mlsanity.com/paper/2304.06815/) (2023)
- [Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference](https://mlsanity.com/paper/2409.01227/) (2024)
- [The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management](https://mlsanity.com/paper/2508.21433/) (2025)
- [AgentFL: Scaling LLM-based Fault Localization to Project-Level Context](https://mlsanity.com/paper/2403.16362/) (2024)
- [Explainable Automated Debugging via Large Language Model-driven Scientific Debugging](https://mlsanity.com/paper/2304.02195/) (2023)
- [Provence: efficient and robust context pruning for retrieval-augmented generation](https://mlsanity.com/paper/2501.16214/) (2025)
- [Diet Code Is Healthy: Simplifying Programs for Pre-trained Models of Code](https://mlsanity.com/paper/2206.14390/) (2022)
- [PISCO: Pretty Simple Compression for Retrieval-Augmented Generation](https://mlsanity.com/paper/2501.16075/) (2025)
- [Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning](https://mlsanity.com/paper/2505.14582/) (2025)
- [Probing Model Signal-Awareness via Prediction-Preserving Input Minimization](https://mlsanity.com/paper/2011.14934/) (2020)

## Built on by (most cited first, 30 of 49)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [Context as a Tool: Context Management for Long-Horizon SWE-Agents](https://mlsanity.com/paper/2512.22087/) (2025)
- [SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents](https://mlsanity.com/paper/2601.16746/) (2026)
- [BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents](https://mlsanity.com/paper/2601.04566/) (2026)
- [Scaling Test-Time Compute for Agentic Coding](https://mlsanity.com/paper/2604.16529/) (2026)
- [SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents](https://mlsanity.com/paper/2606.28434/) (2026)
- [Self-GC: Self-Governing Context for Long-Horizon LLM Agents](https://mlsanity.com/paper/2607.00692/) (2026)
- [Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey](https://mlsanity.com/paper/2601.11655/) (2026)
- [How to Interpret Agent Behavior](https://mlsanity.com/paper/2605.13625/) (2026)
- [SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent](https://mlsanity.com/paper/2605.24468/) (2026)
- [Agentic Software Issue Resolution with Large Language Models: A Survey](https://mlsanity.com/paper/2512.22256/) (2025)
- [SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness](https://mlsanity.com/paper/2609.20519/) (2026)
- [Do LLMs Benefit From Their Own Words?](https://mlsanity.com/paper/2602.24287/) (2026)
- [From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents](https://mlsanity.com/paper/2605.21996/) (2026)
- [CoACT: Action-Preserving Observation Compression for Coding Agents](https://mlsanity.com/paper/2607.02911/) (2026)
- [Turning Interaction History into Execution State: A Runtime Layer for Long-Horizon Coding Agents](https://mlsanity.com/paper/2608.00808/) (2026)
- [SWE-Prime: Fewer Trajectories, Better Performance](https://mlsanity.com/paper/2608.27449/) (2026)
- [Diagnosing and Mitigating Context Rot in Long-horizon Search](https://mlsanity.com/paper/2606.29718/) (2026)
- [The Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent Behavior](https://mlsanity.com/paper/2608.11386/) (2026)
- [ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs](https://mlsanity.com/paper/2608.25992/) (2026)
- [PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents](https://mlsanity.com/paper/2602.23668/) (2026)
- [View-oriented Conversation Compiler for Agent Trace Analysis](https://mlsanity.com/paper/2603.29678/) (2026)
- [AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents](https://mlsanity.com/paper/2605.26596/) (2026)
- [Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories](https://mlsanity.com/paper/2605.29893/) (2026)
- [SWE-Pruner Pro: The Coder LLM Already Knows What to Prune](https://mlsanity.com/paper/2607.18213/) (2026)
- [CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents](https://mlsanity.com/paper/2607.22711/) (2026)
- [Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation](https://mlsanity.com/paper/2608.26195/) (2026)
- [Last Step Matters: Early Uncertainty Cannot Predict Failure in Long-Horizon Agents](https://mlsanity.com/paper/2608.29685/) (2026)
- [ObjectGraph: From Document Injection to Knowledge Traversal -- A Native File Format for the Agentic Era](https://mlsanity.com/paper/2604.27820/) (2026)
- [Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing](https://mlsanity.com/paper/2606.03618/) (2026)

## Abstract (arXiv)

Multi-turn agent systems based on Large Language Models (LLMs) have become increasingly popular for software engineering tasks. While LLM agents demonstrate promising effectiveness, the high computational cost of input tokens due to ever-growing trajectories remains a significant efficiency concern. Efficiency has been largely overlooked in existing studies and agent products, and this paper addresses this gap by introducing an inference-time trajectory reduction approach that reduces computational costs. By analyzing existing agent trajectories, we demonstrate that useless, redundant, and expired information is widespread across trajectories. Such waste can be identified and reduced without compromising the agent's performance. We propose a simple yet effective trajectory reduction approach, AgentDiet, which automatically removes such waste during agent execution. We implement AgentDiet on a top-performing coding agent, and our evaluation on two LLMs and two benchmarks shows that AgentDiet can reduce input tokens by 39.9%-59.7% and the total computational cost by 21.1%-35.9%, while maintaining the same agent performance. These results indicate that inference-time trajectory reduction is a promising direction for agent systems.