Hacktoberfest 2026: le issue che i maintainer hanno segnato per ottobre, aperte e adatte ai principianti. Sfoglia le issue Hacktoberfest

Encountering Empty Patches and Severe Looping Issues while Testing the swe-bench_verified Dataset using Openhands Framework

Aperta
#14 0 commenti 0 reazioni 0 assegnatari Vedi su GitHub

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
4/5
Tempo stimato
3-5 giorni
Idoneità per principianti
25/100
Tipo di issue
Bug
Chiarezza
Da chiarire
Stato di attività
Ferma
Stack tecnologico
python
Ambito
ai, testing-qa

Direzione di ricerca

Inizia riproducendo il report con Openhands CodeActAgent su swe-bench_verified utilizzando il modello Seed-coder, un deployment vllm, il parallelismo a cinque vie e un limite di 120 passaggi. Esamina i risultati con patch vuote e i fallimenti ripetuti di execute_bash descritti nell’issue. Il lavoro è completato quando sono state identificate le cause dell’omissione delle patch e dei cicli, quindi è stata documentata o implementata una correzione verificata.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

I have been testing the swe-bench_verified dataset using the Seed-coder-8b-instruct model along with the Openhands framework. Out of 179 test cases, the accuracy achieved was only 3.9%, which is significantly lower than the reported 11.2% in the paper.

Key Findings:

Empty Patches: During the testing process, I observed that the Seed-coder model produced many empty patches, which seems to be the primary reason for the low solution rate. Out of the 179 test cases, only 7 were solved, 37 produced patches, and 138 did not produce any patches at all.

Looping Issues: Additionally, I encountered significant looping issues during inference. For instance, the system keeps repeating similar tasks without making progress, as shown in the following example:
{
"role": "assistant",
"content": "<function=execute_bash><parameter=command> grep -rn 'ORDER BY' /workspace/django__django__3.0/django/db/models/sql/compiler.py:86-100 "
},
{
"role": "user",
"content": "EXECUTION RESULT of [execute_bash]: grep: /workspace/django__django__3.0/django/db/models/sql/compiler.py:86-100: No such file or directory [The command completed with exit code 2.] [Current working directory: /workspace/django__django__3.0] [Python interpreter: /opt/miniconda3/envs/testbed/bin/python] [Command finished with exit code 2]"
},
{
"role": "assistant",
"content": "<function=execute_bash><parameter=command> grep -rn 'ORDER BY' /workspace/django__django__3.0/django/db/models/sql/compiler.py:257-300 "
},
{
"role": "user",
"content": "EXECUTION RESULT of [execute_bash]: grep: /workspace/django__django__3.0/django/db/models/sql/compiler.py:257-300: No such file or directory [The command completed with exit code 2.] [The command finished with exit code 2]"
},
{
"role": "assistant",
"content": "<function=execute_bash><parameter=command> grep -rn 'ORDER BY' /workspace/django__django__3.0/django/db/models/sql/compiler.py:359-400 "
}
Additional Observations:

Looping Issue: In total, 66 test cases out of the 179 displayed looping behavior during inference.

Excessive Inference Steps: 114 test cases exceeded 120 rounds of inference, with 5 test cases exhibiting both looping and excessive rounds.

Experimental Setup:
Openhands Framework: Maximum inference steps set to 120; using CodeActAgent with parallelism set to 5.

Seed-coder 7b: Temperature set to 0.0; using OpenAI parameter format and deployed locally with vllm. Maximum model length is 32768.

Could you kindly assist in resolving these issues or provide any insights on potential causes?

Lingua principale
Nessun dato sulla lingua
Stelle
759
Fork
60
Metriche di merge delle PR
Nessuna PR unita negli ultimi 30g

Preparare l'ambiente

Questo progetto non fornisce container di sviluppo, Dockerfile né guida per i contributori, quindi l'ambiente è a tuo carico: parti dal suo README e consulta la nostra guida al primo contributo per i passaggi generali.

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di ByteDance-Seed/Seed-Coder

Tutte le issue di ByteDance-Seed/Seed-Coder

Issue simili

Altre issue su AI Infra & Agents

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.