Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning

• URL: http://arxiv.org/abs/2608.24338v1
• Date: Tue, 25 Aug 2026 10:01:56 GMT
• Title: Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning
• Abstract summary: Selective Regenerative Decoding routes each candidate to discard, keep, or refine only the degraded portion of the suffix.<n>SRD achieves a provable 1.28-to-1.36-fold gain in sample efficiency over rejection sampling.<n>Across MATH500, GPQA Diamond, HotpotQA, and AlpacaEval with multiple generation-reward model pairs, SRD matches Best-of-N accuracy with substantially fewer generated tokens.
• Score: 12.065412919637525
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Inference-time decoding methods improve LLM reasoning by exploring multiple candidate trajectories, yet treat each trajectory as atomic: either retaining it whole or discarding it irreversibly. This wastes computation on partially promising candidates whose high-quality prefixes are abandoned alongside degraded suffixes. We introduce Selective Regenerative Decoding (SRD), which routes each candidate to discard, keep, or refine only the degraded portion of the suffix while preserving the useful prefix of borderline candidates, without requiring a larger target model. Under mild assumptions, SRD achieves a provable 1.28-to-1.36-fold gain in sample efficiency over rejection sampling with strictly higher expected trajectory quality, with the gain growing as the candidate pool grows. Across MATH500, GPQA Diamond, HotpotQA, and AlpacaEval with multiple generation-reward model pairs, SRD matches Best-of-N accuracy with substantially fewer generated tokens and outperforms speculative rejection in low-compute regimes. By enabling segment-level intervention rather than whole-trajectory selection, SRD opens a previously underexplored region of the accuracy-compute tradeoff for inference-time reasoning.

Related papers

• ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping [79.1905186547363]
  ResiSpec is a framework that strategically reforms the proposal distribution during verification.<n>It prevents candidate obsolescence and achieves up to 1.92$times$ speedup over state-of-the-art multi-candidate methods.
  arXiv  Detail & Related papers  (2026-08-25T11:25:55Z)
• Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding [92.1521161575198]
  We introduce Confident Decoding, a training-free decoding strategy that dynamically selects the most reliable near-final layer.<n> Experiments across dense and Mixture-of-Experts LLMs demonstrate consistent gains on challenging reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-06-20T07:03:26Z)
• How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings? [58.740078141879984]
  Machine learning models often degrade when they are deployed on a target distribution that differs from the source distributions they were trained on.<n>Recent work in causality-based domain generalization has shown how shared causal structure can induce invariant predictors.<n>In this paper, we study when full or partial causal knowledge can provably improve supervised domain adaptation.
  arXiv  Detail & Related papers  (2026-06-10T21:07:49Z)
• Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability [15.77992479706947]
  Inference-Time Scaling (ITS) has largely succeeded in verifiable domains like math and coding.<n>However, extending ITS to tasks prone to systematic failure typically relies on costly external solvers or brittle, model-based verifiers.<n>Our pipeline applies seamlessly across broad-purpose, domain-specialized, and multimodal architectures.
  arXiv  Detail & Related papers  (2026-06-07T21:43:37Z)
• ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning [69.64972562984882]
  We propose ThoughtFold, a framework that leverages fine-grained preference learning to redundant explorations for efficient reasoning.<n>We show that ThoughtFold significantly enhances efficiency.<n>It reduces the token usage of DeepSeek-R1-Distill-Qwen-7B by approximately 56% while maintaining state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2026-06-02T11:21:27Z)
• Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning [32.295907409325615]
  Training large language models to reason with search engines via reinforcement learning is hindered by a credit assignment problem.<n>We propose SLATE, a framework built on two complementary ideas.<n> Experiments on seven QA benchmarks confirm that SLATE consistently outperforms both sparse-reward and process-reward baselines.
  arXiv  Detail & Related papers  (2026-02-26T19:05:40Z)
• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection [0.9499594220629591]
  Adrial prompt attacks can significantly alter the reliability of Retrieval-Augmented Generation (RAG) systems.<n>We present a novel method that applies Differential Evolution (DE) to optimize adversarial prompt suffixes for RAG-based question answering.
  arXiv  Detail & Related papers  (2025-07-20T16:48:20Z)
• Uncertainty-Penalized Direct Preference Optimization [52.387088396044206]
  We develop a pessimistic framework for DPO by introducing preference uncertainty penalization schemes. The penalization serves as a correction to the loss which attenuates the loss gradient for uncertain samples. We show improved overall performance compared to vanilla DPO, as well as better completions on prompts from high-uncertainty chosen/rejected responses.
  arXiv  Detail & Related papers  (2024-10-26T14:24:37Z)

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.