y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#beam-search News & Analysis

4 articles tagged with #beam-search. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles
AIBullisharXiv – CS AI · May 127/10
🧠

Entropy-informed Decoding: Adaptive Information-Driven Branching

Researchers introduce Entropy-informed Decoding (EDEN), a novel framework that optimizes how large language models generate text by dynamically adjusting computational effort based on output uncertainty. The method matches or exceeds the performance of traditional beam search while using fewer computational expansions, particularly improving results on complex tasks like mathematical reasoning and code generation.

AINeutralarXiv – CS AI · Jun 106/10
🧠

STORM: Stepwise Token Optimization with Reward-Guided Beam Search

Researchers introduce STORM, a self-supervised framework that optimizes lexical query expansion for information retrieval by using BM25 reward signals during generation. The approach enables smaller language models (0.6B-8B parameters) to match larger proprietary rewriters while maintaining BM25's speed efficiency, and demonstrates zero-shot transfer across 18 languages.

AINeutralarXiv – CS AI · May 286/10
🧠

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?

Researchers demonstrate that memory mechanisms in multi-trajectory LLM agents produce inconsistent results depending on the inference strategy used, revealing that previous evaluations conflated memory abstraction properties with inference method effects. The study systematically evaluates four memory methods across three inference strategies on tool-use benchmarks, showing that reflection, fact extraction, and observation injection each perform optimally under different conditions.