Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction¶
🕒 Published (v1): 2026-07-02 06:27 UTC · Source: Arxiv · link
Why this paper was selected
Repo-scale vulnerability reproduction agent with strategy-grounded learning — strong SE+agent benchmark
Ask a follow-up
Open an assistant pre-loaded with this paper's context.
💬 Ask ChatGPT✦ Ask Claude
TL;DR¶
Mastermind is a dual-loop planner–executor framework for repository-scale vulnerability reproduction that separates transferable strategy learning from task-specific experience. A trainable Planner (Qwen3.6-35B-A3B) learns compact natural-language strategies via SFT and milestone-based GRPO, while frozen Executors (GPT-5.5, GPT-5.4 mini, GLM 5.1) instantiate those strategies as PoC rollouts. On CyberGym, this achieves 84.5% pass rate with GPT-5.5, versus 63.0% for Best-of-8 sampling.
Problem¶
LLM agents capable of executing repository-level commands still fail at strategic decisions—where to inspect, what input grammar to target, when to revise hypotheses. With a fixed GPT-5.5 executor, one-shot attempts solve only 23.5% of CyberGym tasks, exposing a planning bottleneck that better execution alone cannot fix. Existing approaches either learn high-level plans without preserving task-local memory, or store experience without updating the planner.
Method¶
Mastermind decomposes the problem into four components operating in two loops:
- Curator activates task-local experience (prior strategy/outcome records, failed hypotheses, verifier milestones) before each attempt and appends new records after verification.
- Planner (Qwen3.6-35B-A3B, trainable) emits a compact natural-language Strategy (capped at 2,000 tokens, median 700–1,100 tokens) describing where to inspect, what input structure to target, and how to validate the PoC. It does not issue shell commands.
- Executor (frozen) translates the Strategy into repository navigation, file edits, shell commands, and PoC submissions via CyberGym.
- Verifier scores each Rollout against CyberGym's milestone hierarchy (m0–m7).
Experience loop: verifier results update curator experience for the next attempt.
Policy loop: GRPO updates Planner weights using rewards from completed rollouts.
Training reward: $\(R(s, y) = \log\!\left(1 + r_{\text{milestone}}(m(y))\right) + \gamma_\ell f_\ell(s) + p_{\text{status}}(y)\)$ where \(f_\ell(s) = \mathbf{1}[s\text{ valid}]\max(0,\, 1 - n_s/T_{\text{strat}})\) penalizes trajectory-length drift, and \(p_{\text{status}} \leq 0\) penalizes timeouts. Advantages are normalized within same-task groups: \(\hat{A}_i = (R_i - \bar{R}_{\text{group}}) / (\sigma_{\text{group}} + \epsilon)\).
Slot-conditioned diversity: each 8-way GRPO group is seeded with eight distinct investigation biases (minimal-reproducer, parser-format, bounds-allocation, lifetime-state, etc.) to prevent strategy collapse.
SFT warm-starts the Planner on stepwise strategy transitions extracted from Claude Code and Codex trajectories, teaching it to revise rather than repeat.
Key Contributions¶
- Strategy bottleneck identification: controlled ablations (Null Strategy 23.5% vs. Soft Oracle 39.5% M7 pass rate under identical executor/workspace) demonstrate strategy quality has a causal effect on reproduction success, independent of execution capability.
- Dual-loop framework: separates Planner weight updates (transferable cross-task reasoning) from Curator experience (volatile task-local facts), assigning each knowledge type to the appropriate substrate.
- Executor-agnostic transferability: a single trained Planner improves GPT-5.4 mini from 45.0% → 60.0% and GLM 5.1 from 58.5% → 71.0% without modifying either executor backbone.
- Milestone-based GRPO: replaces a sparse binary success signal with an 8-level milestone schedule (m0–m7), enabling dense gradient for long-horizon RL over repository-scale tasks.
Results¶
- GPT-5.5 executor: Mastermind 84.5% (169/200 tasks) vs. Best-of-8 63.0% (126/200), iterative improvement 77.0% (154/200), open-book PoC context 60.0% (120/200), one-shot 23.5% (47/200).
- GPT-5.4 mini executor: Mastermind 60.0% vs. baseline 45.0%.
- GLM 5.1 executor: Mastermind 71.0% vs. baseline 58.5%.
- Strategy sensitivity (fixed GPT-5.4 mini): Soft Oracle 39.5%, Hard Oracle 32.0%, Zero-shot Planner 24.0%, Null Strategy 23.5%—showing that an executable strategy outperforms even ground-truth solution context provided directly.
- Rollout efficiency: sequential iterative improvement reaches 154/200 with 753 rollouts vs. Best-of-8 at 126/200 with 1,600 rollouts; Mastermind further improves over this at comparable or fewer rollouts.
- Training: 260-task split; evaluation: 200-task held-out split, stratified, seed 42.
Limitations¶
- Evaluation confined to CyberGym (memory-safety/sanitizer crashes from ARVO and OSS-Fuzz); generalization to other SE task types is undemonstrated.
- Executor rollouts carry a 900-second wall-clock timeout; no action- or token-count caps, making compute costs dependent on hosted service quotas and potentially difficult to reproduce exactly.
- Hard Oracle (ground-truth solution provided) reaches only 32.0%—lower than Soft Oracle—suggesting the executor cannot always convert complete information into a working PoC, a residual execution bottleneck the framework does not address.
- GRPO training is run over 260 tasks; scalability and data efficiency at larger task pools are not reported.
- Strategy diversity relies on slot-conditioned prompting with eight fixed bias slots; this is a heuristic and may not adequately cover all vulnerability classes.
Relevance to Agentic AI / LLM Agents¶
Mastermind directly addresses the planning–acting split that is central to multi-step LLM agent design: it operationalizes the hypothesis that compact, intermediate-level plans are the correct learning unit for long-horizon agentic tasks, rather than full action trajectories. The demonstration that a single trained Planner transfers across frozen Executors speaks directly to modular agent architecture, where planning and execution can be upgraded independently. The dual-loop design—policy loop for cross-task generalization, experience loop for within-task memory—offers a concrete instantiation of how episodic and parametric memory should be separated in agentic systems. The slot-conditioned diversity mechanism and milestone-shaped reward are immediately applicable to other long-horizon agentic RL settings beyond cybersecurity.