arXiv Computation and Language
How Do Small Coding Agents Use Code Graphs and Embeddings?
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Machine Learning
Jul 10
DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks
arXiv:2607. 07946v1 Announce Type: cross Abstract: DeepSWE is a benchmark of 113 original, long-horizon software engineering tasks for evaluating coding agents.
arXiv Machine Learning
Jun 11
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
arXiv:2606. 12344v1 Announce Type: new Abstract: General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and prediction contract required for scoring.
arXiv AI
Jul 14
What Context Does a Coding Agent Actually Need to Act?
arXiv:2607. 09691v1 Announce Type: cross Abstract: A modern coding agent can hold an entire repository in its context window.
arXiv AI
Jul 24
ExecuGraph: A Multi-Agent, Execution-Grounded Framework for Reliable Backend Code Synthesis with Large Language Models
arXiv:2607. 20499v1 Announce Type: new Abstract: Large Language Models generate plausible backend code, but a single-pass paradigm provides no guarantee of correctness or runtime reliability.
arXiv Computation and Language
Aug 28
Agents Don't Paginate: First-Chunk Selection for LLM Tool Responses
The paper investigates why large‑language‑model coding agents rarely request a second chunk of tool output, focusing on the precision‑at‑1 rate ($p_1$) of the gold item appearing first in the first chunk. In a benchmark of 500 software‑engineering tasks, the authors compare six value functions and find that increasing $p_1$ does not systematically improve downstream accuracy; the agent can recover the correct answer from any position within the chunk. Adding file‑metadata signals to a keyword scorer actually reduces $p_1$, while a parameter‑free keyword scorer improves $p_1$ but still fails to boost overall accuracy.
arXiv AI
Aug 7
CodeGrep: An RL-Trained Retrieval Agent for LLM Coding Agents
arXiv:2608. 05886v1 Announce Type: cross Abstract: Modern LLM coding agents such as Claude Code and OpenHands share a common inefficiency: they spend much of their token budget finding the file to patch, rather than patching it.