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.
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:2606. 02438v1 Announce Type: new Abstract: Learned heuristics have recently become a competitive alternative to traditional domain-independent heuristics for satisficing planning.
arXiv:2607. 17710v1 Announce Type: new Abstract: Large Language Models (LLMs) have had a remarkable impact across many areas of machine learning.
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: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).
arXiv:2503. 19990v4 Announce Type: replace Abstract: Many real-world applications of spatial intelligence, such as robotic control, autonomous driving, and automated assembly, require spatial reasoning across multiple sequential steps.
arXiv:2606. 00618v2 Announce Type: replace Abstract: Generative models have emerged as a powerful paradigm for AI planning, yet their performance remains constrained by the training data distribution.
arXiv:2606. 00618v1 Announce Type: new Abstract: Generative models have emerged as a powerful paradigm for AI planning, yet their performance remains constrained by the training data distribution.
arXiv:2605. 28566v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, yet their standard generation process -- auto-regressive token prediction -- is inherently myopic and prone to cascading errors.
ReAct-style LLM agents often rediscover the same reasoning routines across problems, yet leave those routines trapped in transient scratchpads. We introduce Reasoning Primitive Induction, a single-pass method that mines successful ReAct traces, clusters recurrent reasoning moves, and converts the most frequent moves into a compact library of typed pseudo-tools.
arXiv:2506.21734v4 Announce Type: replace Abstract: Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language...