arXiv Machine Learning
Subgoal Search For Complex Reasoning Tasks
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jul 28
How Transformers Learn to Plan via Multi-Token Prediction
arXiv:2604. 11912v2 Announce Type: replace-cross Abstract: While next-token prediction (NTP) has been the standard objective for training language models, it often struggles to capture global structure in reasoning tasks.
arXiv AI
2d ago
Improving Math Reasoning through Value-guided Informative Search
The paper introduces APIVIS, a training-time framework that integrates finite-budget Gumbel search into reinforcement learning with verifiable rewards (RLVR) for mathematical reasoning. APIVIS combines direct and searched responses within each rollout group, uses selective supervision on search-improved tokens, and applies value-guided selection to improve verifier rewards at each searched state. Experiments on standard mathematical reasoning benchmarks and various model scales show significant performance gains over existing search-based methods.
arXiv AI
Jun 2
LLM-Evolved Pattern Generators for Optimal Classical Planning
arXiv:2606. 02438v1 Announce Type: new Abstract: Learned heuristics have recently become a competitive alternative to traditional domain-independent heuristics for satisficing planning.
arXiv Machine Learning
Jul 21
Planning with Transformers: Chain of Computation and Structured Context Windows
arXiv:2607. 17710v1 Announce Type: new Abstract: Large Language Models (LLMs) have had a remarkable impact across many areas of machine learning.
arXiv AI
Jul 7
ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization
arXiv:2607. 05185v1 Announce Type: new Abstract: Compositional generalization, the ability to understand and produce novel combinations of known components, remains a fundamental challenge for modern artificial intelligence.
arXiv AI
Jun 4
Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
arXiv:2601. 15158v4 Announce Type: replace-cross Abstract: Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought).