---
type: "raw_signal"
id: "software-engineering-agents-such-as-agentless-swe-agent-47e5d7"
slug: "software-engineering-agents-such-as-agentless-swe-agent-47e5d7"
title: "Software-engineering agents such as Agentless, SWE-agent, OpenHands, and Claude Code repeatedly generate five kinds of intermediate information."
description: "Microsoft and Georgia Tech researchers published ORACLE-SWE, a study comparing five intermediate information signals used in repository-level software-engineering agent workflows: reproduction tests, regression tests, edit locations, execution context, and API usage."
retrieval_nugget: "Microsoft and Georgia Tech researchers published ORACLE-SWE, a study comparing five intermediate information signals used in repository-level software-engineering agent workflows: reproduction tests, regression tests, edit locations, execution context, and API usage."
observed_at: "2026-10-20"
record_date: "2026-10-20"
date_kind: "observed_at"
why_it_matters: "Microsoft and Georgia Tech researchers published ORACLE-SWE, a study comparing five intermediate information signals used in repository-level software-engineering agent workflows: reproduction tests, regression tests, edit locations, execution context, and API usage. The paper measures how oracle-provided and agent-extracted signals contribute to final task success. It reports a consistent contrib"
novelty: "notable"
verification_level: "source-linked"
signal_type: "research"
source_platform: "arxiv.org"
topics: ["agent-workflows","claude","claude-code"]
entities: ["ORACLE-SWE","Microsoft","Georgia Institute of Technology","SWE-bench","SWE-bench-Live"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "ORACLE-SWE systematically compares five intermediate SWE-agent signals and measures their effects on task success, releasing an oracle-signal dataset and evaluation methodology."
prior_refs: ["memory:7cc08b47-ed81-81b9-a154-27a21ef8bfb8","memory:936f5cfe-a103-8060-ada8-a6c5e7bd0148"]
source_url: "https://arxiv.org/html/2604.07789v3"
source_urls: ["https://arxiv.org/html/2604.07789v3"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:software-engineering-agents-such-as-agentless-swe-agent-47e5d7"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/software-engineering-agents-such-as-agentless-swe-agent-47e5d7/","markdown":"https://newruntime.com/signals/software-engineering-agents-such-as-agentless-swe-agent-47e5d7.md","json":"https://newruntime.com/signals/software-engineering-agents-such-as-agentless-swe-agent-47e5d7.json"}
---

# Software-engineering agents such as Agentless, SWE-agent, OpenHands, and Claude Code repeatedly generate five kinds of intermediate information.

## Retrieval answer

Microsoft and Georgia Tech researchers published ORACLE-SWE, a study comparing five intermediate information signals used in repository-level software-engineering agent workflows: reproduction tests, regression tests, edit locations, execution context, and API usage.

Microsoft and Georgia Tech researchers published ORACLE-SWE, a study comparing five intermediate information signals used in repository-level software-engineering agent workflows: reproduction tests, regression tests, edit locations, execution context, and API usage. The paper measures how oracle-provided and agent-extracted signals contribute to final task success. It reports a consistent contribution ordering: Reproduction Test > Execution Context approximately equal to API Usage > Edit Location > Regression Test. The authors also quantify the gap between agent-extracted signals and their oracle counterparts. The study frames these signals as measurable targets for SWE-agent improvement; its findings are tied to the paper’s experimental setup and do not establish a universal ranking across all coding tasks or systems. Source: https://arxiv.org/html/2604.07789v3

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Agent Workflows](https://newruntime.com/topics/agent-workflows.md): Explore the agent-workflows topic hub.
- topic hub: [Claude](https://newruntime.com/topics/claude.md): Explore the claude topic hub.
- topic hub: [Claude Code](https://newruntime.com/topics/claude-code.md): Explore the claude-code topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)