Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap

• URL: http://arxiv.org/abs/2604.15075v1
• Date: Thu, 16 Apr 2026 14:39:36 GMT
• Title: Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap
• Abstract summary: Atropos is a predictive early-termination analysis and hotswap technique.<n>It aims to improve the cost-benefit trade-off for LLM-based agents that use self-consistency.<n>ATROPOS achieves 74.35% of the performance of closed LLMs with as low as only 23.9% of the cost.
• Score: 4.950224736359097
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Open-weight Small Language Models(SLMs) can provide faster local inference at lower financial cost, but may not achieve the same performance level as commercial Large Language Models (LLMs) that are orders of magnitudes larger. Consequently, many of the latest applications of LLMs, such as software engineering agents, tend to be evaluated on larger models only, leaving the issue of improving the cost-benefit trade-off of such applications neglected. This paper proposes Atropos, a predictive early-termination analysis and hotswap technique that aims to improve the cost-benefit trade-off for LLM-based agents that use self-consistency. The core component of ATROPOS is a predictive model based on structural properties of LLM inferences: after merging multiple agentic inference paths into a graph representation, ATROPOS uses Graph Convolutional Network (GCN) to predict whether an ongoing inference will eventually succeed or not. If an agentic task instance running on the source LLM is predicted to fail, ATROPOS subsequently performs hotswapping, i.e., migrating the on-going inference context onto the more capable target LLM: this is feasible because LLM contexts are stateless. An empirical evaluation of ATROPOS using three recent LLM-based agents shows that ATROPOS can predict early termination of eventually failing inferences with the accuracy of 0.85 at the midpoint of the inference. Hotswapping LLMs for such inferences can convert up to 27.57% of them to be successful. Consequently, ATROPOS achieves 74.35% of the performance of closed LLMs with as low as only 23.9% of the cost.

Related papers

• Beyond LLM-Based Reasoning: Lightweight GNNs for Agent Failure Attribution [47.70578021328887]
  Large language model (LLM)-based multi-agent systems often exhibit complex failure modes.<n>We introduce AFANet, a lightweight graph-based framework that models interaction trajectories through step-level semantic signals and agent-level relationships.<n>Our results suggest that effective agent failure attribution does not require heavy reasoning and a lightweight, structured approach can achieve strong performance.
  arXiv  Detail & Related papers  (2026-08-19T06:16:09Z)
• Selective LLM-Guided Regularization for Enhancing Recommendation Models [7.406718588794206]
  We introduce a model-agnostic and efficient framework that activates LLM based pairwise ranking supervision only when a trainable gating mechanism informs by user history length, item popularity, and model uncertainty predicts the LLM to be reliable.<n> Experiments across multiple datasets show that this selective strategy consistently improves overall accuracy and yields substantial gains in cold start and long tail regimes, outperforming global distillation baselines.
  arXiv  Detail & Related papers  (2025-12-25T06:30:00Z)
• LAET: A Layer-wise Adaptive Ensemble Tuning Framework for Pretrained Language Models [7.216206616406649]
  Large language models (LLMs) like BloombergGPT and FinMA have set new benchmarks across various financial NLP tasks.<n>We propose Layer-wise Adaptive Ensemble Tuning (LAET), a novel strategy that selectively fine-tunes the most effective layers of pre-trained LLMs.<n>Our approach shows strong results in financial NLP tasks, outperforming existing benchmarks and state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2025-11-14T13:57:46Z)
• Reasoning with Confidence: Efficient Verification of LLM Reasoning Steps via Uncertainty Heads [104.9566359759396]
  We propose a lightweight alternative for step-level reasoning verification based on data-driven uncertainty scores.<n>Our findings suggest that the internal states of LLMs encode their uncertainty and can serve as reliable signals for reasoning verification.
  arXiv  Detail & Related papers  (2025-11-09T03:38:29Z)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.<n>LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.<n>Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
  We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems [59.40480894948944]
  Large language model (LLM) empowered agents are able to solve decision-making problems in the physical world. Under this model, the LLM Planner navigates a partially observable Markov decision process (POMDP) by iteratively generating language-based subgoals via prompting. We prove that the pretrained LLM Planner effectively performs Bayesian aggregated imitation learning (BAIL) through in-context learning.
  arXiv  Detail & Related papers  (2024-05-30T09:42:54Z)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [68.29746557968107]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans.<n> Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)
• SMART: Automatically Scaling Down Language Models with Accuracy Guarantees for Reduced Processing Fees [21.801053526411415]
  Large Language Models (LLMs) have significantly boosted performance in natural language processing (NLP) tasks. The deployment of high-performance LLMs incurs substantial costs, primarily due to the increased number of parameters aimed at enhancing model performance. We introduce SMART, a novel framework designed to minimize the inference costs of NLP tasks while ensuring sufficient result quality.
  arXiv  Detail & Related papers  (2024-03-11T17:45:47Z)

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.