Runtime Persistence Agent Evaluation (Anonymous)
Collection
Anonymous double-blind workshop supplement: training traces, eval data and LoRA adapters for a per-turn-cap agent study. • 16 items • Updated
messages listlengths 3 41 |
|---|
[
{
"role": "system",
"content": "You are a CodeAct-style autonomous agent.\n\nYou solve tasks by alternating between:\n1. Natural-language reasoning (plain text), and\n2. Executable simple Python code blob (inside fenced code blocks).\n\nEach step (output) can include at most 1 (one) code block.\n\nBe concis... |
[
{
"role": "system",
"content": "You are a CodeAct-style autonomous agent.\n\nYou solve tasks by alternating between:\n1. Natural-language reasoning (plain text), and\n2. Executable simple Python code blob (inside fenced code blocks).\n\nEach step (output) can include at most 1 (one) code block.\n\nBe concis... |
[
{
"role": "system",
"content": "You are a CodeAct-style autonomous agent.\n\nYou solve tasks by alternating between:\n1. Natural-language reasoning (plain text), and\n2. Executable simple Python code blob (inside fenced code blocks).\n\nEach step (output) can include at most 1 (one) code block.\n\nBe concis... |
[
{
"role": "system",
"content": "You are a CodeAct-style autonomous agent.\n\nYou solve tasks by alternating between:\n1. Natural-language reasoning (plain text), and\n2. Executable simple Python code blob (inside fenced code blocks).\n\nEach step (output) can include at most 1 (one) code block.\n\nBe concis... |
[
{
"role": "system",
"content": "You are a CodeAct-style autonomous agent.\n\nYou solve tasks by alternating between:\n1. Natural-language reasoning (plain text), and\n2. Executable simple Python code blob (inside fenced code blocks).\n\nEach step (output) can include at most 1 (one) code block.\n\nBe concis... |
[
{
"role": "system",
"content": "You are a CodeAct-style autonomous agent.\n\nYou solve tasks by alternating between:\n1. Natural-language reasoning (plain text), and\n2. Executable simple Python code blob (inside fenced code blocks).\n\nEach step (output) can include at most 1 (one) code block.\n\nBe concis... |
[
{
"role": "system",
"content": "You are a CodeAct-style autonomous agent.\n\nYou solve tasks by alternating between:\n1. Natural-language reasoning (plain text), and\n2. Executable simple Python code blob (inside fenced code blocks).\n\nEach step (output) can include at most 1 (one) code block.\n\nBe concis... |
[
{
"role": "system",
"content": "You are a CodeAct-style autonomous agent.\n\nYou solve tasks by alternating between:\n1. Natural-language reasoning (plain text), and\n2. Executable simple Python code blob (inside fenced code blocks).\n\nEach step (output) can include at most 1 (one) code block.\n\nBe concis... |
[
{
"role": "system",
"content": "You are a CodeAct-style autonomous agent.\n\nYou solve tasks by alternating between:\n1. Natural-language reasoning (plain text), and\n2. Executable simple Python code blob (inside fenced code blocks).\n\nEach step (output) can include at most 1 (one) code block.\n\nBe concis... |
[
{
"role": "system",
"content": "You are a CodeAct-style autonomous agent.\n\nYou solve tasks by alternating between:\n1. Natural-language reasoning (plain text), and\n2. Executable simple Python code blob (inside fenced code blocks).\n\nEach step (output) can include at most 1 (one) code block.\n\nBe concis... |
End of preview. Expand in Data Studio
Training Traces
Anonymous supplementary release for a double-blind workshop submission. This dataset
holds the teacher agent traces used to fine-tune the paper's LoRA adapters (see the
sibling cap-sweep-eval-data release and the ten adapter repos alongside this one).
6,000 agent traces total (1,000 per family x runtime combination), produced by an LLM teacher solving each of the paper's three agentic task families -- Opaque Knapsack, navigation, and rule diagnosis -- under two interpreter runtime conditions. Each config is a persistent/stateless pair for one family; all six were used to fine-tune the correspondingly-named LoRA adapters.
Key terms
- Persistent runtime: the Python interpreter keeps all variables alive between
agent steps. An agent can write
total_weight += wand it persists to the next turn. - Stateless runtime: the interpreter resets after every step; nothing carries over automatically, so the agent must re-establish any state it needs each turn.
Format
Each line is a {"messages": [...]} chat-format record (system / user / assistant /
tool turns) suitable for direct SFT ingestion. Records include the full CodeAct-style
system prompt, task prompt, the agent's code blocks and tool outputs (including tool
exceptions), through to task completion.
Provenance
Released anonymously alongside a NeurIPS workshop submission for reproducibility review. Non-anonymous release (paper citation, full code) will follow after the review process concludes.
- Downloads last month
- 27