ReDAct: Uncertainty-Aware Deferral for LLM Agents

• URL: http://arxiv.org/abs/2604.07036v1
• Date: Wed, 08 Apr 2026 12:51:01 GMT
• Title: ReDAct: Uncertainty-Aware Deferral for LLM Agents
• Abstract summary: We propose ReDAct (Reason-Defer-Act) to solve sequential decision-making problems.<n>In ReDAct, an agent is equipped with two LLMs: a small, cheap model used by default, and a large, more reliable but expensive model.<n>We show that deferring only about 15% of decisions to the large model can match the quality of using it exclusively, while significantly reducing inference costs.
• Score: 61.507376922278894
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, LLM-based agents have become increasingly popular across many applications, including complex sequential decision-making problems. However, they inherit the tendency of LLMs to hallucinate, leading to incorrect decisions. In sequential settings, even a single mistake can irreversibly degrade the trajectory, making hallucinations an even bigger problem. Although larger LLMs hallucinate less, they incur a significantly higher per-token cost. In this paper, we address this tradeoff by proposing ReDAct (Reason-Defer-Act). In ReDAct, an agent is equipped with two LLMs: a small, cheap model used by default, and a large, more reliable but expensive model. When the predictive uncertainty of the small model exceeds a calibrated threshold, the decision is deferred to the large model. We evaluate our approach in text-based embodied environments such as ALFWorld and MiniGrid and show that deferring only about 15% of decisions to the large model can match the quality of using it exclusively, while significantly reducing inference costs.

Related papers

• RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment [57.588738943463646]
  Large Language Models (LLMs) have achieved remarkable performance in Machine Translation (MT)<n> deploying them at scale remains prohibitively expensive.<n>We propose textbfRouteLMT, an in-model router that predicts the expected gain by probing the small translators prompt-token representation.
  arXiv  Detail & Related papers  (2026-04-24T13:02:45Z)
• Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap [4.950224736359097]
  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.
  arXiv  Detail & Related papers  (2026-04-16T14:39:36Z)
• 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)
• Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation [66.84286617519258]
  Large language models are transforming social science research by enabling the automation of labor-intensive tasks like data annotation and text analysis.<n>Such variation can introduce systematic biases and random errors, which propagate to downstream analyses and cause Type I (false positive), Type II (false negative), Type S (wrong sign), or Type M (exaggerated effect) errors.<n>We find that intentional LLM hacking is strikingly simple. By replicating 37 data annotation tasks from 21 published social science studies, we show that, with just a handful of prompt paraphrases, virtually anything can be presented as statistically significant.
  arXiv  Detail & Related papers  (2025-09-10T17:58:53Z)
• Cost-Saving LLM Cascades with Early Abstention [1.3108652488669732]
  We investigate the benefits of "early abstention" in LLM cascades.<n>We find that it reduces overall test loss by 2.2% on average across six benchmarks.<n>These gains result from a more effective use of abstention, trading a 4.1% average increase in the overall abstention rate for a 13.0% reduction in cost and a 5.0% reduction in error rate.
  arXiv  Detail & Related papers  (2025-02-13T08:08:39Z)
• Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models [79.46938238953916]
  Fine-tuning large language models (LLMs) to diverse applications is crucial to meet complex demands. Recent studies suggest decomposing a fine-tuned LLM into a base model and corresponding delta weights, which are then compressed using low-rank or low-bit approaches to reduce costs. In this work, we observe that existing low-rank and low-bit compression methods can significantly harm the model performance for task-specific fine-tuned LLMs.
  arXiv  Detail & Related papers  (2024-06-13T07:57:27Z)
• Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection [80.63946798650653]
  Decision centers on whether to use a large LLM with better performance or a smaller one with reduced costs. We propose a simpler solution; we use only the uncertainty of the generations of the small LLM as the decision criterion. Our experiments reveal this simple solution optimally balances cost and performance, outperforming existing methods on 25 out of 27 experimental setups.
  arXiv  Detail & Related papers  (2024-05-03T14:38:59Z)
• The ART of LLM Refinement: Ask, Refine, and Trust [85.75059530612882]
  We propose a reasoning with refinement objective called ART: Ask, Refine, and Trust. It asks necessary questions to decide when an LLM should refine its output. It achieves a performance gain of +5 points over self-refinement baselines.
  arXiv  Detail & Related papers  (2023-11-14T07:26:32Z)
• LoRA ensembles for large language model fine-tuning [35.78186948630364]
  Low-Rank Adapters (LoRA) is a parameter-efficient fine-tuning technique. LoRA represents a very small number of parameters, orders of magnitude less than the underlying pre-trained model. We find that LoRA ensembles, applied on its own or on top of pre-existing regularization techniques, gives consistent improvements in predictive accuracy and uncertainty quantification.
  arXiv  Detail & Related papers  (2023-09-29T16:38:38Z)

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.