Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively

• URL: http://arxiv.org/abs/2506.00396v1
• Date: Sat, 31 May 2025 05:32:12 GMT
• Title: Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively
• Authors: Jiawei Gu, Shangsong Liang,
• Abstract summary: We introduce the 3E Criteria to assess the cost-effectiveness of search strategies.<n>We propose the Speculative Reward Model (SRM), a plug-and-play framework that integrates seamlessly with existing search strategies.<n> Experimental results show that RM reduces costs to 1/10 of the original search framework on average while maintaining effectiveness.
• Score: 13.40488551654639
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Effective decision-making in Large Language Models (LLMs) is essential for handling intricate tasks. However, existing approaches prioritize performance but often overlook the balance between effectiveness and computational cost. To address this, we first introduce the 3E Criteria to systematically assess the cost-effectiveness of search strategies, revealing that existing methods often trade significant efficiency for marginal performance gains. To improve LLM decision-making while maintaining efficiency, we propose the Speculative Reward Model (SRM), a plug-and-play framework that seamlessly integrates with existing search strategies. Specifically, SRM employs an external reward assigner to predict optimal actions, reducing reliance on LLMs' internal self-evaluation. And a speculative verification mechanism is used to prune suboptimal choices and guide the search toward more promising steps. We evaluate SRM on several complex decision-making tasks including mathematical reasoning, planning and numerical reasoning in specialized domains. Experimental results show that SRM reduces costs to 1/10 of the original search framework on average while maintaining effectiveness.

Related papers

• Reasoning Models Can be Easily Hacked by Fake Reasoning Bias [59.79548223686273]
  We introduce THEATER, a comprehensive benchmark to evaluate Reasoning Theater Bias (RTB)<n>We investigate six bias types including Simple Cues and Fake Chain-of-Thought.<n>We identify'shallow reasoning'-plausible but flawed arguments-as the most potent form of RTB.
  arXiv  Detail & Related papers  (2025-07-18T09:06:10Z)
• Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement [101.77467538102924]
  Large reasoning models (LRMs) exhibit overthinking, which hinders efficiency and inflates inference cost.<n>We propose two lightweight methods to enhance LRM efficiency.<n>First, we introduce Efficiency Steering, a training-free activation steering technique that modulates reasoning behavior via a single direction.<n>Second, we develop Self-Rewarded Efficiency RL, a reinforcement learning framework that dynamically balances task accuracy and brevity.
  arXiv  Detail & Related papers  (2025-06-18T17:18:12Z)
• Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing [14.114970711442512]
  This paper introduces Attention Pruning, a fairness-aware simulated annealing approach to prune attention heads in large language models (LLMs)<n>Our experiments show that Attention Pruning achieves up to $40%$ reduction in gender bias and outperforms the state-of-the-art bias mitigation strategies.
  arXiv  Detail & Related papers  (2025-03-20T03:02:32Z)
• Exploring the Necessity of Reasoning in LLM-based Agent Scenarios [74.35956310688164]
  We propose the LaRMA framework, encompassing nine tasks across Tool Usage, Plan Design, and Problem Solving.<n>Our findings address four research questions: LRMs surpass LLMs in reasoning-intensive tasks like Plan Design, leveraging iterative reflection for superior outcomes.<n>LRMs' enhanced reasoning incurs higher computational costs, prolonged processing, and behavioral challenges, including overthinking and fact-ignoring tendencies.
  arXiv  Detail & Related papers  (2025-03-14T04:34:31Z)
• Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solving [55.895917967408586]
  Existing approaches to mathematical reasoning with large language models rely on Chain-of-Thought (CoT) for generalizability or Tool-Integrated Reasoning (TIR) for precise computation.<n>We propose TATA (Teaching LLMs According to Their Aptitude), an adaptive framework that enables LLMs to personalize their reasoning strategy spontaneously.
  arXiv  Detail & Related papers  (2025-02-17T16:56:23Z)
• Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
  We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs)<n>RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness.<n>RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
  arXiv  Detail & Related papers  (2025-01-31T17:19:57Z)
• EVOLvE: Evaluating and Optimizing LLMs For Exploration [76.66831821738927]
  Large language models (LLMs) remain under-studied in scenarios requiring optimal decision-making under uncertainty. We measure LLMs' (in)ability to make optimal decisions in bandits, a state-less reinforcement learning setting relevant to many applications. Motivated by the existence of optimal exploration algorithms, we propose efficient ways to integrate this algorithmic knowledge into LLMs.
  arXiv  Detail & Related papers  (2024-10-08T17:54:03Z)
• Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling [9.44858963874474]
  Self-Consistency mitigates hallucinations in Large Language Models (LLMs) by sampling multiple reasoning paths.<n>We introduce Reasoning-Aware Self-Consistency (RASC), a novel framework that enhances sampling efficiency and reasoning faithfulness.
  arXiv  Detail & Related papers  (2024-08-30T05:14:59Z)
• Efficient Budget Allocation for Large-Scale LLM-Enabled Virtual Screening [0.9558392439655016]
  We consider an LLM-as-human-evaluator approach for conducting screening virtually, thereby reducing the cost burden.<n>We propose using a top-$m$ greedy evaluation mechanism, and design the explore-first top-$m$ greedy (EFG-$m$) algorithm.<n>Surprisingly, we uncover a bonus ranking effect, where the algorithm naturally induces an indifference-based ranking within the selected subset.
  arXiv  Detail & Related papers  (2024-08-18T16:44:41Z)
• On Leveraging Large Language Models for Enhancing Entity Resolution: A Cost-efficient Approach [7.996010840316654]
  We propose an uncertainty reduction framework using Large Language Models (LLMs) to improve entity resolution results. LLMs capitalize on their advanced linguistic capabilities and a pay-as-you-go'' model that provides significant advantages to those without extensive data science expertise. We show that our method is efficient and effective, offering promising applications in real-world tasks.
  arXiv  Detail & Related papers  (2024-01-07T09:06:58Z)
• Multiple Independent DE Optimizations to Tackle Uncertainty and Variability in Demand in Inventory Management [0.0]
  This study aims to discern the most effective strategy for minimizing inventory costs within the context of uncertain demand patterns. To find the optimal solution, the study focuses on meta-heuristic approaches and compares multiple algorithms.
  arXiv  Detail & Related papers  (2023-09-22T13:15:02Z)

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.