What Self-Training Fixes in a Budget-Bound Coding Agent

Abstract: The current paper examines the effectiveness of using rejection-sampling self-training to enhance the performance of a budget constrained coding agent (Gemma 4’s 31B Model) on some repository repair tasks. Three rank-16 QLoRA adapters were trained from 129 public tasks with the successful trajectories verified. A loss mask that is aware of the template did not include any tool outputs and did not pick up any unproductive actions. The baseline thinking-off took an average of 6.0 solves over the two passesof 30 tasks, whereas after round 1 it was 4.5 solves and after round 2 it was 3.0 solves. There was no statistically significant increase in solves in the thinking-on (8.0) vs round 3 (8.5). Round 1 led to a decreased frequency of editing and an increased number of redundant reads, whereas round 2 partly reinstated editing but did not increase task resolution. Context summarization was the most prevalent type, with 39 of the 129 thinking-off and 97 of the 129 thinking-on runs being affected by this type of context summarization. One variant of the prompt was used repeatedly for four different sets of scores—13, 11, 7, and 7/58. The results indicate that the behavior of agents can be modified by limiting the amount of self-training, but that there is no efficacy in task resolution with this limited self-training, and that the variability of the context management, execution cost, and evaluation still plays an important role.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-12
DOI
https://doi.org/10.5281/zenodo.24159157
Primary Topic
Software Engineering Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

What Self-Training Fixes in a Budget-Bound Coding Agent

Moez ur Rehman
Zenodo (CERN European Organization for Nuclear Research)
Software Engineering Research
article

What Self-Training Fixes in a Budget-Bound Coding Agent

Moez ur Rehman
article en

Abstract

Abstract: The current paper examines the effectiveness of using rejection-sampling self-training to enhance the performance of a budget constrained coding agent (Gemma 4’s 31B Model) on some repository repair tasks. Three rank-16 QLoRA adapters were trained from 129 public tasks with the successful trajectories verified. A loss mask that is aware of the template did not include any tool outputs and did not pick up any unproductive actions. The baseline thinking-off took an average of 6.0 solves over the two passesof 30 tasks, whereas after round 1 it was 4.5 solves and after round 2 it was 3.0 solves. There was no statistically significant increase in solves in the thinking-on (8.0) vs round 3 (8.5). Round 1 led to a decreased frequency of editing and an increased number of redundant reads, whereas round 2 partly reinstated editing but did not increase task resolution. Context summarization was the most prevalent type, with 39 of the 129 thinking-off and 97 of the 129 thinking-on runs being affected by this type of context summarization. One variant of the prompt was used repeatedly for four different sets of scores—13, 11, 7, and 7/58. The results indicate that the behavior of agents can be modified by limiting the amount of self-training, but that there is no efficacy in task resolution with this limited self-training, and that the variability of the context management, execution cost, and evaluation still plays an important role.

Zenodo (CERN European Organization for Nuclear Research)
Software Engineering Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon