SERA: Soft-Verified Efficient Repository Agents
Paper • 2601.20789 • Published • 13
Datasets:
messages listlengths 12 148 | instance_id stringlengths 25 25 | tool_json listlengths 3 3 |
|---|---|---|
[
{
"role": "system",
"content": "You are a helpful assistant that can interact with a computer to solve tasks.\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\": \"function\", \"fun... | django_django_f8fab_10143 | [
{
"type": "function",
"function": {
"name": "bash",
"description": "runs the given command directly in bash",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The bash command to execute."
... |
[
{
"role": "system",
"content": "You are a helpful assistant that can interact with a computer to solve tasks.\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\": \"function\", \"fun... | django_django_f8fab_10161 | [
{
"type": "function",
"function": {
"name": "bash",
"description": "runs the given command directly in bash",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The bash command to execute."
... |
[
{
"role": "system",
"content": "You are a helpful assistant that can interact with a computer to solve tasks.\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\": \"function\", \"fun... | django_django_f8fab_10186 | [
{
"type": "function",
"function": {
"name": "bash",
"description": "runs the given command directly in bash",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The bash command to execute."
... |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | django_django_f8fab_10132 | [{"type":"function","function":{"name":"bash","description":"runs the given command directly in bash(...TRUNCATED) |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | django_django_f8fab_10096 | [{"type":"function","function":{"name":"bash","description":"runs the given command directly in bash(...TRUNCATED) |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | django_django_f8fab_10159 | [{"type":"function","function":{"name":"bash","description":"runs the given command directly in bash(...TRUNCATED) |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | django_django_f8fab_10027 | [{"type":"function","function":{"name":"bash","description":"runs the given command directly in bash(...TRUNCATED) |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | django_django_f8fab_10095 | [{"type":"function","function":{"name":"bash","description":"runs the given command directly in bash(...TRUNCATED) |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | django_django_f8fab_10017 | [{"type":"function","function":{"name":"bash","description":"runs the given command directly in bash(...TRUNCATED) |
[{"role":"system","content":"You are a helpful assistant that can interact with a computer to solve (...TRUNCATED) | django_django_f8fab_10169 | [{"type":"function","function":{"name":"bash","description":"runs the given command directly in bash(...TRUNCATED) |
End of preview. Expand in Data Studio
SERA GLM-5.2 Django SWE-Agent — T2 (second-rollout trajectories, r=0 / unverified)
165 software-engineering agent trajectories generated with the SERA SVG pipeline (paper).
- Teacher: GLM-5.2 (temperature 0.6), reasoning traces preserved in
<think>blocks - Harness: SWE-agent (
str_replace_editor,bash,submittools), 75-step cap, SWE-Bench Django container (django__django-7530, base commitf8fab6f9) - Stage: rollout two — a fresh agent solves the synthetic PR generated from rollout one; verification threshold r=0 (all submitted trajectories kept, no recall filter), following SERA §5.1 which finds unverified T2 data equal or better than verified
- Format: one JSON per line:
messages(hermes<tool_call>format),trainkeys (assistant-only) for axolotl,instance_id,tool_json - Tokens (cl100k approx): avg 10.6k, max 33.7k (1 record exceeds 32k), 1.74M total
Training guidance from the SERA paper: train on BOTH rollouts — the Django specialization recipe is 5,000 filtered T1 + 3,000 T2 (§4.3); mixing T1+T2 beats T2-only at equal T2 count (§5.6). Companion set: SERA-GLM5.2-Django-SWEAgent-T1.
- Downloads last month
- 49