Add 7 new papers from April 2026 - #2
Open
botbubble wants to merge 12 commits into
Open
Conversation
Copy link
Copy Markdown
Sorry, something went wrong.
added 12 commits
April 16, 2026 17:14
Papers added: - REAgent (2604.06861) - single_agent: Requirement-Driven LLM Agents for Software Issue Resolution - SWE-AGILE (2604.11716) - single_agent: Dynamic Reasoning Context Management - AgentForge (2604.13120) - multi_agent: Execution-Grounded Multi-Agent Framework - CODESTRUCT (2604.05407) - workflow: Code Agents over Structured Action Spaces (ACL 2026) - SWE-ZERO to SWE-HERO (2604.01496) - sft: Execution-free to Execution-based Fine-tuning - PassRateConstraint (2604.05955) - methods_analysis: Design Constraint Compliance Evaluation - RTMC (2604.11037) - rl: Step-Level Credit Assignment via Rollout Trees
Usage: # List recent papers python scripts/cli_add_paper.py --list # Search python scripts/cli_add_paper.py --search SWE-bench # Add paper to DB python scripts/cli_add_paper.py --short-name TestPaper --title "Test Paper Title" --authors "Author Name" --venue "arXiv 2024" --year 2024 --category single_agent --arxiv https://arxiv.org/abs/... # Add and sync to YAML python scripts/cli_add_paper.py --short-name Test --title Test ... --sync
- SWE-bench Multimodal: 619 → 617 instances (arXiv:2410.03859) - SWE-bench-extra: 2k repos → 1,988 repos, 6.38k → 6,376 instances (HuggingFace nebius/SWE-bench-extra) - Multi-SWE-bench: 76 repos → -, 4,723 → 1,632 instances (arXiv:2504.02605; 4,723 is Multi-SWE-RL) - Add SWE-rebench V2 to table (32,000+ tasks, 20 languages, 3,600+ repos, arXiv:2602.23866)
Added from paper sections (previously missing from table): - OpenSWE: 45,320 envs, 12,800 repos (arXiv:2603.13023) - SWE-Universe: 807,693 envs (arXiv:2602.02361) - Scale-SWE: 100k instances, 5,200 repos (arXiv:2602.09892) - daVinci-Dev: envs available, details on HuggingFace (arXiv:2601.18418) - SWE-Next: 2,308 instances, 3,971 repos (arXiv:2603.20691) - Multi-Docker-Eval: 40 repos, benchmark only (arXiv:2512.06915) Also corrected: - SWE-bench Multimodal: 619 → 617 instances - SWE-bench-extra: 2k → 1,988 repos, 6.38k → 6,376 instances - Multi-SWE-bench: 76 → - repos, 4,723 → 1,632 (RL subset removed)
…ng, trajectory tables)
… trajectory tables
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.
New Papers (April 2026)
This PR adds 7 papers published in April 2026, covering multiple categories:
🤖 Single-Agent Systems
👥 Multi-Agent Systems
🔄 Workflow-Based Methods
📚 Supervised Fine-Tuning (SFT)
🔍 Methods Analysis
🎮 Reinforcement Learning (RL)
Auto-generated by botbubble survey maintenance bot.