← Back to all news
arXiv AI By Ritika Poddar, Aidan Fennelly, Deirdre Murphy, Eric Wolos, Corre L. Steele, Michael Doyle

BUSTA: Teaching Small Language Models to Reason About Binary Execution

Read the original on arXiv AI →

The paper introduces BUSTA, a method for training small language models to reason about binary execution. By fine‑tuning Qwen3‑1.7B and Nemotron‑3‑Nano with Group Relative Policy Optimization, the authors improve the models’ ability to predict input register values for a given x86‑64 basic block, raising accuracy from 73.2% to 85.3% and from 63.3% to 95.2% respectively. The fine‑tuned Nemotron‑3‑Nano achieves performance within four points of frontier models while using far fewer parameters, and the authors release both the fine‑tuned models and the training dataset.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Sep 24

ChipMEM: Verification-Grounded Memory for EDA Agents

ChipMEM introduces a verification‑grounded memory layer for electronic design automation agents that combines cross‑task procedural memory with within‑trajectory statistical guidance. The procedural component stores a skill only after it passes synthesis, simulation, or formal checks, while a Bayesian component ranks recovery strategies based on tool‑call outcomes. Experiments on RTLRewriter‑Bench and CVDP tasks show that ChipMEM improves equivalence‑passing outputs and area metrics compared to agents without memory.

By Abdulrahman AlRabah, Joshua Mabry, Dilek Hakkani-T\"ur, Abdussalam Alawini, Hamid Shojaei, Kartik Hegde, Sandesh Adhikary
llmsagentsbenchmarks
More like this →
arXiv AI
Oct 1

EngramBench: A Capability-Grounded Benchmark for Skill-Evolution Harnesses

EngramBench is a new benchmark designed to evaluate skill evolution in autonomous agents by focusing on genuine capability abstraction rather than solution copying. It includes 30 learning tasks and 13 unseen transfer tasks that require agents to manage complex, multi-hour development cycles with LLM‑simulated users. The study shows that while static skill banks cannot eliminate the need for precise code implementation, they effectively reduce redundant context and cut overall coding time by more than 55%.

By Zhixuan Tan, Pengjie Gu, Zhao Li, Yihan Hu, Xu He, Dong Li, Jianye Hao
llmsagentsbenchmarks
More like this →