arXiv Computation and Language
REWIND: Uncertainty-Guided Trajectory Repair for Test-Time Reasoning
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
Hugging Face Trending Papers
3d ago
REWIND: Uncertainty-Guided Trajectory Repair for Test-Time Reasoning
An early mistake in the generated reasoning can constrain all subsequent reasoning. Repeated-generation methods, like MCMC-based approaches, attempt to improve output quality by sampling multiple gene...
arXiv AI
Aug 26
Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning
Selective Regenerative Decoding (SRD) is a new inference-time decoding method that improves large language model reasoning by allowing segment-level intervention on candidate trajectories. Instead of discarding or keeping entire trajectories, SRD selectively refines only the degraded suffix while preserving useful prefixes, leading to higher expected trajectory quality and better sample efficiency. Experiments on MATH500, GPQA Diamond, HotpotQA, and AlpacaEval show that SRD matches Best-of-N accuracy with fewer generated tokens and outperforms speculative rejection in low‑compute settings.
arXiv AI
Jun 2
Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance
arXiv:2606. 00305v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) improves large language model reasoning by training a student model on trajectories sampled from its own policy under teacher supervision.
arXiv AI
Jun 6
ReTreVal: Reasoning Tree with Validation and Cross-Problem Memory for Large Language Models
arXiv:2601. 02880v2 Announce Type: replace Abstract: Every existing inference-time reasoning framework discards all failure context at problem boundaries, leaving a model solving problem 500 no wiser than it was on problem 1.
arXiv Machine Learning
Jun 18
Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
arXiv:2606. 18844v1 Announce Type: new Abstract: Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution.
arXiv AI
Sep 1
ORDDAR: Observation-Driven Reasoning for Distortion-Resilient Decision, Action, and Cognitive Recovery
arXiv:2608.28704v1 Announce Type: new Abstract: AI agents increasingly perform long-term reasoning, planning, tool use, memory integration, and autonomous decision making, yet erroneous intermediate...