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- 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
How fast it is moving
Often studied with
diffusion modelA type of generative model that learns to reverse a gradual noising process to create data.3 togetherlarge language modelA neural network trained on massive text corpora to generate coherent text and perform diverse language tasks.2 togethertest-time scalingAllocating extra computation during inference to improve output quality.2 togetherThe papers
Most central to this idea first, not most recent.
- Top Universitycs.LG
Confidence 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.
The Ohio State University, University of Pennsylvania · Oct 2026
- Big Techcs.IR
AI search averages 1.8 times the query throughput of rivals
Ginger is a C++ library that speeds up approximate nearest neighbor search by 1.8x on average while using less memory.
Google Research, KIT · Nov 2026
- Big Techcs.LG
AI models factor larger numbers, but costs grow exponentially
A transformer using discrete diffusion and beam search factors 68-bit semiprimes but scales exponentially with bit length.
Google DeepMind · Nov 2026
- Big Techcs.AR
Weight mapping algorithm for 3D AI chips boosts throughput 2x
CAMP improves compute utilization on 3D-IMC arrays from 42.4% to 60.3%, achieving up to 2.0x throughput and 1.74x end-to-end gains over prior mapping.
IBM Research · Nov 2026
- Big Techcs.AI
Reinforcement learning adapts diffusion models to large routing problems
ResizeCO adapts a diffusion model trained on small routing instances to large TSP and CVRP instances via reinforcement learning, setting a new state of the art for short run times.
Bar-Ilan University, NVIDIA · Oct 2026
- Chinese Techcs.LG
Counterfactual prompts let beam search self-distill language models at inference
Test-time self-distillation using counterfactual contexts and beam search improves language model generation without retraining.
Huawei Noah’s Ark Lab, UCL Centre for AI · Oct 2026
- Top Universitycs.LG
Generative models as proposal distributions improve long-horizon decision making
Generative Trajectory Planning uses a generative model as a proposal distribution for action sequences enabling efficient long-horizon planning.
Harvard University · Oct 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.