Searcharxiv⌕ Search

arXiv subjects

Martin Schroder

Publications and source records attributed to Martin Schroder.

3 recordsLinked to original sources

The Frontier Must Grow - Self-proposed, interpreter-labelled training roughly doubles a 4B model's accuracy on a fresh exam as its verified frontier grows

A model can learn from problems it poses itself when an executable oracle supplies the answers. Qwen3-4B proposed Lua 5.1 programs; those it predicted wrong at least once in four samples joined a pool labelled by the interpreter, each round adding twice as many programs as the last (300, 900, 2100 in total), and each round trained a fresh adapter from the base on the pool. On the original exam the procedure met its registered criterion, an item-level test of each adapter against its predecessor. On a 2340-item exam drawn afterwards, accuracy rose from 8.3% to 16.7%; that follow-up's registered criteria were not met because round 1 gained nothing, while rounds 2 and 3 added 5.0 and 2.9 points on average, both intervals above zero. One fit on the same amount of base-proposed frontier data reached 14.6%, so the rounds' 2.1-point advantage is inconclusive. Three earlier registered series met no per-lineage criterion, and the same loop showed no gain on repository tasks or for a 27B agent in those configurations.

cs.AI↗

AutoScrum: Automating Project Planning Using Large Language Models

Recent advancements in the field of large language models have made it possible to use language models for advanced reasoning. In this paper we leverage this ability for designing complex project plans based only on knowing the current state and the desired state. Two approaches are demonstrated - a scrum based approach and a shortcut plan approach. The scrum based approach executes an automated process of requirements gathering, user story mapping, feature identification, task decomposition and finally generates questions and search terms for seeking out domain specific information to assist with task completion. The shortcut approach looks at most recent snapshot of the current and desired state and generates the next most reasonable task to do in order to get to the desired state as quickly as possible. In this paper we automate everything using a novel concept of "Language Programs". These are programs written in natural language designed to process input data through the language model. Guidance language is used for all LLM programs. All demo source code for this paper is available at https://github.com/autoscrum/autoscrum

cs.AI↗

Broken symmetry and the variation of critical properties in the phase behaviour of supramolecular rhombus tilings

The degree of randomness, or partial order, present in two-dimensional supramolecular arrays of isophthalate tetracarboxylic acids is shown to vary due to subtle chemical changes such as the choice of solvent or small differences in molecular dimensions. This variation may be quantified using an order parameter and reveals a novel phase behaviour including random tiling with varying critical properties as well as ordered phases dominated by either parallel or non-parallel alignment of neighbouring molecules, consistent with long-standing theoretical studies. The balance between order and randomness is driven by small differences in the intermolecular interaction energies, which we show, using numerical simulations, can be related to the measured order parameter. Significant variations occur even when the energy difference is much less than the thermal energy highlighting the delicate balance between entropic and energetic effects in complex self-assembly processes.

cond-mat.stat-mech↗