Pith. sign in

REVIEW 20 cited by

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.19324 v3 pith:VE4MLESY submitted 2025-01-31 cs.CL cs.AI

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

classification cs.CL cs.AI
keywords decodingmodelspeculativetargetefficiencyllmsreasoningreward-guided
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs). RSD synergistically combines a lightweight draft model with a more powerful target model, incorporating a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness. RSD employs a process reward model to evaluate intermediate decoding steps and dynamically decide whether to invoke the target model, optimizing the trade-off between computational cost and output quality. We theoretically demonstrate that a threshold-based mixture strategy achieves an optimal balance between resource utilization and performance. Extensive evaluations on challenging reasoning benchmarks, including Olympiad-level tasks, show that RSD delivers significant efficiency gains against decoding with the target model only (up to 4.4x fewer FLOPs), while achieving significant better accuracy than parallel decoding method on average (up to +3.5). These results highlight RSD as a robust and cost-effective approach for deploying LLMs in resource-intensive scenarios. The code is available at https://github.com/BaohaoLiao/RSD.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 20 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing

    cs.CL 2026-06 unverdicted novelty 7.0

    LBR performs token-level test-time scaling via local branch routing on hidden states, enabling end-to-end RL training and improving Pass@1 and Pass@32 on math benchmarks over CoT and RLVR baselines.

  2. Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing

    cs.CL 2026-06 unverdicted novelty 7.0

    Local Branch Routing (LBR) is a token-level framework for test-time scaling in language models that uses local branch hidden states for routing and supports end-to-end RL, showing gains in Pass@1 and Pass@32 on math r...

  3. KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human Difficulty

    cs.CL 2026-06 unverdicted novelty 7.0

    KCSAT-ML benchmark supplies human error rates for math problems and DRG metric exposes that model accuracy collapses on high-human-error items while test-time scaling shows non-monotonic gains and alignment failures.

  4. Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost

    cs.AI 2026-05 conditional novelty 7.0

    Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.

  5. When to Plan: Learning to Select Between Reactive Control and Deliberative Planning

    cs.AI 2026-07 conditional novelty 6.0

    An RL-trained meta-policy that uses ensemble uncertainty to choose between a cheap reactive policy and costly planning reaches goals faster than fixed baselines and adapts as the reactive policy improves.

  6. Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making

    cs.CL 2026-07 conditional novelty 6.0

    Hidden-state traces of frozen LLMs/VLMs can be read by lightweight trained heads to predict when to defer, clarify, call tools, or abstain, cutting routed inference cost 27–90%.

  7. Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning

    cs.CL 2026-06 unverdicted novelty 6.0

    PRP introduces proactive routing via Draft Rating Learning and Joint Rating Learning to route queries early between draft and target models for efficient multimodal reasoning.

  8. ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning

    cs.AI 2026-06 unverdicted novelty 6.0

    ThoughtFold applies introspective redundancy detection within correct CoT trajectories to create sub-trajectory spectra, then uses masked preference optimization to penalize redundant explorations, yielding 56% token ...

  9. Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing

    cs.CL 2026-05 unverdicted novelty 6.0

    PPOW uses window-level RL with cost-aware speedup and proximity rewards plus adaptive divergence-aware windowing to reach 6.29-6.52 acceptance lengths and 3.39-4.36x speedups in speculative decoding.

  10. Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning

    stat.ML 2026-05 unverdicted novelty 6.0

    A conformal procedure for CoT replaces majority voting with weighted aggregation and calibrates abstention to guarantee low confident-error rates, achieving 90.1% selective accuracy on GSM8K by abstaining on under 5% ...

  11. Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration

    cs.LG 2026-05 unverdicted novelty 6.0

    SPEX delivers 1.2-3x speedup on ToT algorithms via speculative path selection, dynamic budget allocation, and adaptive early termination, reaching up to 4.1x when combined with token-level speculative decoding.

  12. Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration

    cs.LG 2026-05 unverdicted novelty 6.0

    SPEX accelerates Tree-of-Thought LLM reasoning 1.2-3x via speculative path selection, dynamic budget allocation across queries, and adaptive early termination, with up to 4.1x when combined with token speculative decoding.

  13. Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning

    cs.AI 2026-05 unverdicted novelty 6.0

    A small RL-trained policy for stepwise model routing between LLM sizes improves the accuracy-cost tradeoff on math benchmarks over handcrafted strategies and matches large process reward model methods.

  14. Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards

    cs.LG 2025-10 conditional novelty 6.0

    MAHALO aligns LLMs to multiple objectives in one model via per-objective action heads and PRM-guided decoding, improving math, value, and tutoring metrics jointly.

  15. Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs

    cs.CV 2025-05 unverdicted novelty 6.0

    Chain-of-Focus enables VLMs to adaptively search and zoom on important image areas via a two-stage SFT and RL pipeline on a custom 3K-sample dataset, yielding 5% gains on the V* benchmark across resolutions from 224 to 4K.

  16. Is Your Model Thinking or Just Stagnating? PUMA: Diagnosing Reasoning Pathology via Phase-Momentum Alignment

    cs.AI 2026-07 conditional novelty 5.0

    PUMA detects when a reasoning model's entropy drop aligns with hidden-state momentum, truncates at that point, and reports improved accuracy-efficiency on 1.5B-32B reasoning models.

  17. MixReasoning: Switching Modes to Think

    cs.AI 2025-10 conditional novelty 5.0

    A reasoning model can cut token usage by roughly a third to a half without losing accuracy if it switches to brief output on low-uncertainty steps and expands only at high-uncertainty forks.

  18. Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance

    cs.CV 2025-09 conditional novelty 5.0

    IGG, an attention-based reweighting of classifier-free guidance, concentrates guidance on important tokens and modestly improves FID/IS in scale-wise autoregressive image generation.

  19. Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

    cs.CL 2025-03 accept novelty 5.0

    A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.

  20. The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

    cs.CL 2026-06 unverdicted novelty 4.0

    A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.