← All concepts

beam search

Beam search is a method for generating sequences or plans by maintaining a fixed number of top candidates at each step, known as the beam width. This balance between completeness and computational cost makes it efficient for tasks like language generation and decision making.

The papers show that beam search is especially robust for complex, multi-step reasoning and planning problems. They develop variants like Confidence-Filtered Beam Search to improve sample efficiency, use beam search to approximate optimal policies derived from language model probabilities, and integrate it with diffusion models for routing tasks. These approaches achieve strong performance without requiring additional training data or reward models, highlighting beam search's versatility.

Papers
7
Released code
0
First seen
Oct 2026
Latest
Nov 2026

7 papers in the last two months, against 0 in the two before.

Start here

The paper to read first
  1. 1Confidence filtering gives beam search stronger test-time scaling guarantees

    Confidence-filtered beam search reduces test-time sample complexity from quadratic to nearly linear and provably outperforms sequence-level inference.

    Oct 2026

The papers

Most central to this idea first, not most recent.

Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.