The paper introduces a method for learning search control policies that dramatically reduce the space required for heuristic plan search. By using an indexical policy with registers and a special choose rule, the approach ensures that every execution is bounded polynomially in the number of objects, allowing a depth‑first procedure to find plans in polynomial space. The learned policies, obtained via a language‑model guided counterexample loop, successfully solve 1,709 of 1,890 IPC 2023 Learning Track tasks and the Autoscale Agile suite, outperforming state‑of‑the‑art planners such as LAMA, BFWS, and Levitron.
arXiv:2607. 17710v1 Announce Type: new Abstract: Large Language Models (LLMs) have had a remarkable impact across many areas of machine learning.
The paper introduces neuro‑symbolic computer use, a method that learns reusable policies to execute recurring computer workflows efficiently. Instead of re‑planning each run, the learned policy encodes stable decisions (ordering, variables, loops, branches) into executable code while delegating observation‑dependent decisions to neural models. Using neuro‑symbolic policy iteration, the approach iteratively refines the policy from a single agent trajectory, diagnoses failures, and revises the code with a coding model, achieving superior Pass^3 scores and significant reductions in per‑run cost and latency on OSWorld‑Verified and ScienceBoard benchmarks.
GADAR (Generalizing Across Domains via Action Ranking) is a learned policy for classical planning that accepts a domain description as input and constructs grounded actions in unseen domains without search. It uses a three‑layer architecture—lifted domain, binding, and chain layers—to embed domain structure, tie action applicability to lifted preconditions, and capture schema dependencies. In zero‑shot experiments across eight benchmark domains, a single GADAR model trained on seven domains solves 58.3% of test instances, matching closely the performance of domain‑specific models and outperforming random choice and a representation lacking the chain layer.
arXiv:2607. 13389v1 Announce Type: new Abstract: Reinforcement Learning (RL) post-training is increasingly used to adapt foundation models for reasoning, planning, and feedback-driven robot-learning pipelines, but constrained post-training resources are often summarized by a single total FLOP budget.
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:2610.08246v1 Announce Type: new Abstract: Frontier large language models (LLMs) can generate heuristic functions that guide search to achieve state-of-the-art performance in satisficing plannin...
arXiv:2608. 05085v1 Announce Type: cross Abstract: Systems that automate scientific discovery must repeatedly decide which experiment to run, which hypothesis to test, which tool to build, and when to stop.
The paper introduces Divide-and-Remember (D&R), a recursive memory method for vision-language-action (VLA) policies that optimises memory by maximizing the conditional mutual information between actions and memory given observations. D&R recursively divides the full history into top‑K selections over 2K tokens, using a shared lightweight selector across all recursion blocks to handle unbounded histories efficiently. Evaluated on the RoboMME benchmark of 16 long‑horizon manipulation tasks, D&R achieves state‑of‑the‑art success rates with consistent gains across all suites while using only 64 tokens, and similar improvements are observed in real‑robot experiments.
arXiv:2607. 11725v1 Announce Type: cross Abstract: Prefabricated prefinished volumetric construction moves most building work into module factories, whose production floor operates as a flexible job shop.
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.
arXiv:2607. 15459v1 Announce Type: new Abstract: A trained deep reinforcement learning policy is a black box, and we ask whether it can be made explainable by rewriting it as an executable logic program that reproduces its behaviour and that a person can read, a logic engine can run, and an optimizer can edit.
arXiv:2606. 20002v1 Announce Type: cross Abstract: This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based AI agent gets deployed in an environment, it solves a long sequence of tasks while continuously exploring the environment, learning from its own experiences, and iteratively self-updating its context about the environment, thereby achieving progressively better performance on future tasks conditioned on the updated context.