feat: ProgramBench reverse-engineering environment#1351
Draft
sethkarten wants to merge 4 commits into
Draft
Conversation
Verifiers.v1 environment where an RLM agent reconstructs source code from compiled binaries, scored by fraction of pytest tests passed. Key implementation decisions: - golang:1.22-bookworm / gcc:13-bookworm for standard langs; custom Rust image with pre-warmed cargo registry for Rust tasks - apt-get update + pip --break-system-packages required for pytest on Debian 12 (PEP 668 restriction) - Test archives hidden from agent at setup; uploaded at scoring time following the rlm_swe_v1 pattern - Scoring re-runs compile.sh with PATH prepended for toolchain binaries so agents that omit PATH export still get scored correctly - go_subset.jsonl contains 5 smoke-test tasks; full dataset on PrimeIntellect/programbench-processed (HF private) Smoke test: 17/36 tests passed (reward=0.472) with gpt-4.1-mini on antonmedv__fx.86d0d34, confirming end-to-end pipeline works. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…2a, fasttext, brotli, halite, blake3)
…ces fragile shell heredocs)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
environments/programbench/— a verifiers.v1RLMenvironment where an agent reconstructs source code from compiled binaries, scored by fraction of pytest tests passedantonmedv__fx.86d0d34withgpt-4.1-miniKey design decisions
golang:1.22-bookworm,gcc:13-bookworm, custom Rust image with pre-warmed cargo registrypip --break-system-packagesafterapt-get update(Debian 12 / PEP 668 requirement)rlm_swe_v1pattern)compile.shwith PATH prepended so agents that omit PATH export still get correct scoresPrimeIntellect/programbench-processed(private HF); 5-task Go smoke subset indata/go_subset.jsonlTest plan
prime env install programbenchsucceedsvf-eval programbench -a '{"filter_language":"go","max_tasks":1}' -n 1 -r 1 -d -vreturns non-zero rewardvf-eval programbench -a '{"filter_language":"go"}' -n 5 -r 1scripts/build_binaries_linux.sh) to enable agent probingdocker/build.sh)Pending follow-up
binary_hf_repo/binary_hf_filenamefields)🤖 Generated with Claude Code