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.
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.
ProofEvolve is a neuro‑symbolic framework that evolves formally verified symbolic proof structures alongside neural models to expand the knowledge boundary in automated theorem proving. The neural component proposes variation operators such as decompositions, repairs, and schema recombinations, while the Lean kernel verifies every proof transition, ensuring formal soundness. Across three competition‑level Lean benchmarks, ProofEvolve achieves the highest average solve rate among evaluated proof systems.
arXiv:2606. 20068v1 Announce Type: new Abstract: While reinforcement learning from verifiable rewards (RLVR) typically has relied on a single binary verification signal, symbolic proof assistants in formal reasoning offer rich, fine-grained structured feedback.
arXiv:2608. 15700v1 Announce Type: new Abstract: Background: Distillation of training targets generated thru search/planning has proven useful in reinforcement learning, but search can take exceedingly long.
The paper introduces Actor‑Critic with Action Chunking (AC2), a method that assigns credit to short action chunks instead of entire trajectories, enabling policy updates without waiting for terminal rewards. AC2 employs local readiness, reference solutions, and 10k‑token chunks to make critic‑based credit assignment reliable. Experiments on Qwen3‑4B with FineProofs‑RL show AC2 surpasses GRPO’s peak validation score while using 2.5× fewer decoding FLOPs and fewer training steps.
arXiv:2505. 13372v2 Announce Type: replace Abstract: Recent work investigated the use of Reinforcement Learning (RL) for the synthesis of heuristic guidance to improve the performance of temporal planners when a domain is fixed and a set of training problems (not plans) is given.
The paper introduces a system that automatically generates macro-operators—composite actions that compress recurring sequences of individual actions—by discovering causally linked action pairs in training data. It also prunes unused predicates from the symbolic state, reducing the number of predicates evaluated at each search node. These combined optimizations shorten the effective planning horizon and yield up to a 4.6× speedup, enabling the solution of long sequential tasks that baseline methods cannot solve.
arXiv:2607. 28135v1 Announce Type: new Abstract: Machine learning for combinatorial optimization typically relies on neural constructors trained via reinforcement learning on large offline datasets for a fixed problem class-incurring high pretraining costs and generalizing poorly outside the training distribution.
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. 18767v3 Announce Type: replace-cross Abstract: In Machine-Assisted Theorem Proving, a theorem proving agent searches for a sequence of expressions and tactics that can prove a statement in a proof assistant.
arXiv:2304.10041v2 Announce Type: replace Abstract: This work investigates formal policy synthesis for continuous-state stochastic dynamic systems subject to high-level specifications expressed in li...
arXiv:2512.13095v3 Announce Type: replace Abstract: To address the limited capability expansion and low sample efficiency of Reinforcement Learning (RL), recent methods have integrated ''hints'' into...