← Back to all news
arXiv Machine Learning

RadonBench: A Benchmark of Classical and Learning-Guided Search Techniques for Problems in Combinatorial Geometry

arXiv:2610. 33259v1 Announce Type: new Abstract: Classical optimization and learning-guided search offer complementary approaches to open problems in discrete mathematics, but their outputs are difficult to compare when search spaces, validity checks, and stopping rules differ.

Related stories

Hugging Face Trending Papers
Jun 24

Geometry-Aware MCTS for Extremal Problems in Combinatorial Geometry

We study certain extremal problems in combinatorial geometry that ask about configurations of points in an $n \times n$ grid that satisfy strict, global geometric constraints. Classical exact solvers suffer from combinatorial explosion for these types of problems, and standard reinforcement learning and transformer-based models struggle with the sparse reward "validity cliff" and quadratic token-consumption limits.

llmsreinforcement-learningefficiency
More like this →
arXiv Machine Learning
Jun 30

Actively Learning Halfspaces without Synthetic Data

arXiv:2509. 20848v2 Announce Type: replace-cross Abstract: In the classic point location problem, one is given an arbitrary dataset $X \subset \mathbb{R}^d$ of $n$ points with query access to an unknown halfspace $f : \mathbb{R}^d \to \{0,1\}$, and the goal is to learn the label of every point in $X$.

By Hadley Black, Kasper Green Larsen, Arya Mazumdar, Barna Saha, Geelon So
More like this →
Hugging Face Trending Papers
Sep 17

Stable Movement for Nondual Lipschitz Convex Optimization: Efficiency and Nearly Optimal Oracle Rates

We study efficient algorithms for realizing the first-order oracle complexity of optimization of $G$-Lipschitz convex functions with respect to the $\ell_{q}$-norm over an $\ell_{p}$-ball of radius $R$, where $1\leq p,q\leq \infty$. For $p<q$, we obtain error $\widetilde{O}_{p,q}(GR/T^{1/p-(1/q-1/2)_{+}})$ after $T$ oracle queries, efficiently realizing the nearly optimal rates of (MBG+26), thereby resolving the nonsmooth end of the COLT 2015 open problem (Guz15b).

More like this →
arXiv AI
Sep 25

Reinforcement Learning with Verifiable Rewards for Small Search Agents

The paper introduces Reinforcement Learning with Verifiable Rewards (RLVR) applied to small search agents, specifically training a Qwen3.5-0.8B model with Group Relative Policy Optimization and an interleaved Wikipedia-search tool on the MuSiQue dataset. Experiments varying reward shapes across three seeds show that RLVR can achieve a 3.8‑fold improvement over an untrained baseline, with the best run reaching a 0.352 average exact match. The study finds that the sparse exact‑match reward, standard in larger models, performs poorly for small models, indicating that reward design must be tailored rather than scaled down from large‑model recipes.

By Gaurisankar Jayadas, Aske Plaat, \'Alvaro Serra-G\'omez, Sandheep P
agentsnlpreinforcement-learningefficiencybenchmarks
More like this →
arXiv AI
Oct 9

Learning How to Search for Plans with Exponentially Less Space

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.

By Dominik Drexler, Simon St{\aa}hlberg, Markus Fritzsche, Blai Bonet
llms
More like this →