arXiv:2509. 18930v3 Announce Type: replace-cross Abstract: Neural algorithmic reasoning (NAR) is a paradigm that trains neural networks to execute classic algorithms by supervised learning.
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:2602.13106v2 Announce Type: replace-cross Abstract: In recent years, there has been growing interest in understanding neural architectures' ability to learn to execute discrete algorithms, a li...
The paper presents an approach to automated theorem proving by framing the construction of clausal connection tableaux as a policy in a transition system. It introduces a graph neural network that scores proof edits based on structure, trained via imitation learning from existing proofs. Experiments on M2k, MPTP2078-bushy, and TPTP v9.2.1 show that the learned policies solve up to 46% more problems than leanCoP and find proofs in an order of magnitude fewer steps.
The paper introduces a novel end‑to‑end, size‑agnostic graph reinforcement learning framework for the one‑dimensional bin packing problem (1D‑BPP). It models packing as a Markov decision process on an item‑compatibility graph, where a graph neural network actor‑critic policy learns to merge compatible partial bins. Empirical results on the BPPLIB benchmark show that the learned policy reduces the mean optimality gap of a constructive heuristic from 2.66 % to 2.31 %, performs competitively against other learned methods, and outperforms a state‑of‑the‑art learned solver on the hardest benchmark family.
arXiv:2602. 07832v3 Announce Type: replace-cross Abstract: Process rewards have been widely used in deep reinforcement learning to improve training efficiency, reduce variance, and prevent reward hacking.
arXiv:2504. 18587v2 Announce Type: replace-cross Abstract: Reinforcement learning has emerged as a powerful approach for improving the reasoning capabilities of large language models, as demonstrated by systems such as OpenAI's O1~\cite{o1} and DeepSeek-R1~\cite{r1}.
Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented large language models (LLMs). Existing approaches typically rely on large-scale supervised datasets, costly reasoning annotations, and expensive intermediate step verification, resulting in substantial training overhead.
arXiv:2510. 04140v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a widely adopted technique for enhancing the reasoning ability of Large Language Models (LLMs).
The paper introduces Graph-Guided Quasimetric Dense Reward (G2QDR), a framework that learns a state connectivity model to predict pairwise connectivity strengths in asymmetric environments. These strengths are converted into scalar auxiliary dense rewards, offering continuous guidance across hierarchical levels. G2QDR can be integrated into any existing Goal-Conditioned Hierarchical Reinforcement Learning architecture and shows empirical performance improvements in sparse reward settings with modest computational cost.
arXiv:2607. 16421v1 Announce Type: new Abstract: It has long been recognized that humans have the ability to switch between fast, reactive decision-making and slower, deliberative planning.
arXiv:2606. 25832v1 Announce Type: new Abstract: Achieving strong optimization generalization across diverse optimization problems while requiring limited training resources remains a challenging problem for optimization-oriented large language models (LLMs).
The paper presents an end‑to‑end framework that uses constraint‑oriented hypergraphs and reinforcement learning to solve vehicle routing problems. It introduces a dynamic hyperedge reconstruction strategy for better hypergraph representation and a double‑pointer attention decoder for iterative solution generation. Experiments on benchmark datasets show that the method removes the need for complex heuristic operators while improving solution quality.