Improving the Efficiency of LLM Agent Systems through Trajectory Reduction

• URL: http://arxiv.org/abs/2509.23586v1
• Date: Sun, 28 Sep 2025 02:43:41 GMT
• Title: Improving the Efficiency of LLM Agent Systems through Trajectory Reduction
• Authors: Yuan-An Xiao, Pengfei Gao, Chao Peng, Yingfei Xiong,
• Abstract summary: This paper introduces an inference-time trajectory reduction approach to reduce the cost of agents.<n>We show that AgentDiet can reduce input tokens by 39.9% 59.7%, or the final computational cost by 21.1% 35.9%, while maintaining the same agent performance.
• Score: 6.087402350213508
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-turn agent systems based on Large Language Models (LLMs) have been increasingly popular for software engineering tasks. While LLM agents show decent effectiveness, the high computational cost of input tokens due to the ever-growing trajectory remains an efficiency concern for their applications. Efficiency is largely neglected in existing studies and agent products, and this paper fills the gap by introducing an inference-time trajectory reduction approach to reduce the cost of agents. Through analyzing existing agent trajectories, we demonstrate that useless, redundant, and expired information is widespread in all trajectories, which can be identified and reduced without harming the agent's performance. We then design a simple yet effective trajectory reduction approach, AgentDiet, which automatically removes such waste information. We implement AgentDiet on a top-performing coding agent, and the evaluation on two LLMs and two benchmarks shows that AgentDiet can reduce input tokens by 39.9% ~ 59.7%, or the final computational cost by 21.1% ~ 35.9%, while maintaining the same agent performance. This indicates that trajectory reduction is a promising direction for agent systems.

Related papers

• DLLM Agent: See Farther, Run Faster [94.74432470237817]
  Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties.<n>We study this in a controlled setting by instantiatingDLLM and AR backbones within the same agent workflow.<n>We find thatDLLM Agents are on average over 30% faster end to end than AR agents, with some cases exceeding 8x speedup.
  arXiv  Detail & Related papers  (2026-02-07T09:01:18Z)
• Scaling Small Agents Through Strategy Auctions [6.863341991827782]
  We show that small agents' performance fails to scale with task complexity on deep search and coding tasks.<n>We introduce Strategy Auctions for Workload Efficiency, an agent framework inspired by freelancer marketplaces.<n>We show that SALE reduces reliance on the largest agent by 53%, lowers overall cost by 35%, and consistently improves upon the largest agent's pass@1.
  arXiv  Detail & Related papers  (2026-02-02T20:05:51Z)
• EET: Experience-Driven Early Termination for Cost-Efficient Software Engineering Agents [22.98266662213199]
  EET is an experience-driven early termination approach for software engineering agents.<n>It reduces the cost of SE agents while preserving task performance.<n>EET consistently reduces total cost by 19%-55%, with negligible loss in resolution rate.
  arXiv  Detail & Related papers  (2026-01-09T13:01:49Z)
• DEPO: Dual-Efficiency Preference Optimization for LLM Agents [75.6723341304463]
  We propose DEPO, a dual-efficiency preference optimization method that jointly rewards succinct responses and fewer action steps.<n>Experiments on WebShop and BabyAI show that DEPO cuts token usage by up to 60.9% and steps by up to 26.9%, while achieving up to a 29.3% improvement in performance.
  arXiv  Detail & Related papers  (2025-11-19T12:38:43Z)
• AgentEvolver: Towards Efficient Self-Evolving Agent System [51.54882384204726]
  We present AgentEvolver, a self-evolving agent system that drives autonomous agent learning.<n>AgentEvolver introduces three synergistic mechanisms: self-questioning, self-navigating, and self-attributing.<n>Preliminary experiments indicate that AgentEvolver achieves more efficient exploration, better sample utilization, and faster adaptation compared to traditional RL-based baselines.
  arXiv  Detail & Related papers  (2025-11-13T15:14:47Z)
• Efficient Agents: Building Effective Agents While Reducing Cost [48.65558640786415]
  Large Language Model (LLM)-driven agents have enabled sophisticated systems to tackle complex, multi-step tasks.<n>This work presents the first systematic study of the efficiency-effectiveness trade-off in modern agent systems.
  arXiv  Detail & Related papers  (2025-07-24T17:56:51Z)
• The Real Barrier to LLM Agent Usability is Agentic ROI [110.31127571114635]
  Large Language Model (LLM) agents represent a promising shift in human-AI interaction.<n>We highlight a critical usability gap in high-demand, mass-market applications.
  arXiv  Detail & Related papers  (2025-05-23T11:40:58Z)
• Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments [54.67512489842682]
  Large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments.<n>We take a first step toward exploring the early-exit behavior for LLM-based agents.
  arXiv  Detail & Related papers  (2025-05-23T08:23:36Z)
• Exploring Expert Failures Improves LLM Agent Tuning [74.0772570556016]
  We propose Exploring Expert Failures (EEF), which identifies beneficial actions from failed expert trajectories.<n>EEF successfully solves some previously unsolvable subtasks and improves agent tuning performance.
  arXiv  Detail & Related papers  (2025-04-17T17:53:54Z)
• AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration [45.46295333090397]
  We propose AgentDropout, which identifies redundant agents and communication across different communication rounds.<n>AgentDropout achieves an average reduction of 21.6% in prompt token consumption and 18.4% in completion token consumption, along with a performance improvement of 1.14 on the tasks.
  arXiv  Detail & Related papers  (2025-03-24T17:04:55Z)
• TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents [10.798271657186492]
  This paper advocates Trajdeleter, the first practical approach to trajectory unlearning for offline RL agents. The key idea of Trajdeleter is to guide the agent to demonstrate deteriorating performance when it encounters states associated with unlearning trajectories. Extensive experiments conducted on six offline RL algorithms and three tasks demonstrate that Trajdeleter requires only about 1.5% of the time needed for retraining from scratch.
  arXiv  Detail & Related papers  (2024-04-18T22:23:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.