SkillForge: Compositional Skill Synthesis with Verification-in-the-Loop for Generating Formally Verified Dafny Programs

Generating formally verified programs from natural language remains challenging: existing approaches either produce code in a single pass without recourse when verification fails, or rely on open-ended agentic reasoning that is non-deterministic and opaque. We introduce SKILLFORGE, a framework that decomposes formal code synthesis into a library of atomic, reusable skills, each targeting a specific subtask such as specification inference, body synthesis, invariant generation, error diagnosis, or targeted repair, and defined by a prompt template, tool binding, and decidable success criterion. A verification-driven harness orchestrates these skills: it submits candidates to the Dafny verifier, diagnoses failures into structured categories, deterministically routes to the appropriate repair skill, and iterates until formal correctness is proved or a budget is exhausted. On a curated benchmark of natural language to Dafny specification pairs, SKILLFORGE substantially outperforms both state-of-the-art agentic approaches (including ReAct-style agents, MCTS-based repair, and RL-guided verification) and traditional iterative baselines, while requiring fewer tokens and lower latency. Ablation studies confirm that every skill contributes measurably, and the harness converges rapidly with the majority of programs verified on the first attempt.

Narcissus: Program Synthesis Using Context-Aware LLM Approximations

Large language models (LLMs) excel at programming, but not when the task fixes the target language: prompted with a grammar rare in their training data, their programs usually break the grammar or fail the given specification. Enumerative synthesizers search the space of syntactically correct programs systematically guided by LLMs; the state of the art guides them by approximating LLM proposals into rule frequencies, which loses where each construct belongs and prunes every rule the proposals miss, exactly when the proposals are wrong. We present Narcissus, a synthesizer that keeps the proposals as syntax trees and scores each expansion of a candidate program in its context: does a proposal with the same surrounding structure continue the same way, and does the expansion rebuild a fragment the proposals repeat? A regularization term keeps every rule reachable, so wrong proposals delay the solution but cannot hide it. Across five domains and two search backends, Narcissus beats static guidance at every budget and consistently outperforms re-prompting the LLM to fix its own proposals; it reaches proposal-like programs an order of magnitude sooner and solves $40\%$ of ARC tasks where the raw proposals solve $13\%$, all without a single LLM call during search.

ExpConCAD: Experience-Guided Text-to-CAD Generation from Shape Descriptions with Implicit Spatial Constraints

Text-to-CAD aims to generate executable CAD programs from natural-language descriptions. However, real-world descriptions are often underspecified and omit critical spatial constraints required for valid CAD construction, a challenge that has been largely overlooked by existing methods. In this paper, we argue that missing spatial constraints should be inferred with respect to the underlying construction structure and informed by reusable design experience. Based on this insight, we propose ExpConCAD, an experience-enhanced framework for implicit spatial constraint completion. ExpConCAD first recovers the intended construction structure and constraint scopes, then retrieves relevant constraint-completion experience for similar scopes to complete the missing spatial constraints, and finally generates executable CadQuery programs. Extensive experiments demonstrate the effectiveness of ExpConCAD and provide insights into the role of construction structure understanding and experience memory in spatial constraint completion. Our code is available at: https://github.com/Hotjiashell/ExpConCAD.

P$^{3}$: Joint Program-and-Proof Planning for Verified Code Generation

Verified code generation asks a large language model (LLM) to generate both an executable program and a machine-checkable proof that the program meets a formal specification, promising software that is correct by construction. The de facto workflow decouples the two halves of the problem: first synthesize a program, then attempt to prove it correct. We observe that this sequential pipeline can be both ineffective and inefficient in practice. A program generated without anticipating its proof can be subtly incorrect or structurally difficult to verify, forcing the LLM into brittle repair loops that alternate between patching the code and patching the proof. Inspired by Dijkstra's view that a program and its correctness argument should be developed hand in hand, we propose $P^3$, an LLM-based agentic workflow that first derives a unified program-and-proof plan from the specification, then elaborates the implementation and proof scaffold under this shared plan. To evaluate verified code generation in realistic settings, we further introduce Lean4Commit0, a repository-derived, library-level benchmark built by extracting core APIs from real-world software repositories and translating their requirements, including relational specifications across APIs, into Lean tasks. Using four frontier LLM backends, we evaluate $P^3$ on Verina, AlgoVeri, and our Lean4Commit0 benchmark, where it achieves the highest solve rate in every benchmark--model setting. Compared with the stronger baseline, it improves solve rates by 4.6--11.2 percentage points and reduces per-task API cost by up to roughly 40\% and wall-clock time by up to roughly 37\% on the difficult subset of each benchmark. A targeted ablation further shows gains of 3.3--8.3 points over implementation-only planning, isolating the benefit of planning the program and proof jointly.

Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer

Decomposition-based Programming-by-example (PBE) scales performance by splitting tasks into subtasks that a learned synthesizer solves: a decomposer predicts intermediate subgoals, and a synthesizer generates programs conditioned on them. Current approaches train the decomposer to imitate ground-truth ( GT) subgoals, implicitly treating decomposition quality as intrinsic to the task. We challenge this assumption: for bounded solvers with fixed inductive biases, GT decompositions reflect the annotator's factorization choices - not the solver's search dynamics. A decomposer trained to match GT decompositions may therefore propose subgoals that are logically valid yet intractable for the solver. We propose Solver-Aware Decomposition (SAD), a training framework that retains supervised training on GT subgoals as a structural scaffold, while additionally optimizing the decomposer via direct feedback from a frozen synthesizer. Subgoals are rewarded based on the synthesizer's loss on the target program - a signal of subtask difficulty that encourages decompositions the solver can act on. Our experiments reveal an accuracy paradox: higher agreement with GT decompositions does not improve synthesis success - even though the synthesizer was trained on the very same GT data the decomposer is optimized to mimic. SAD instead learns decompositions that trade GT alignment for solver tractability, yielding consistent gains in synthesis and end-to-end task accuracy across two PBE domains. Moreover, SAD solves tasks that a GT decomposition oracle fails - empirical evidence that GT decompositions are not universally optimal for bounded solvers, and that decomposition quality is solver-relative, not intrinsic.

SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch

LLM-based agents excel at software engineering tasks where an existing codebase provides context, but constructing a program from scratch remains fundamentally harder. Recent benchmarks such as ProgramBench quantify this gap: given only natural-language documentation and an execute-only binary as a behavioral oracle, even frontier models solve fewer than 1% of instances. Existing frameworks conflate documentation reading, behavioral exploration, and code synthesis into a single pass, causing agents to probe insufficiently, lose behavioral intent as context drifts, and propagate early misinterpretations into the final implementation. Inspired by classical requirements engineering, we argue that behavioral specification elicitation should be a first-class phase that precedes implementation. We present SpecFirst, a two-stage framework that forces the specification elicitation before code synthesis. A dedicated spec agent first probes the binary and combines observations with documentation into a structured specification. Next, a code synthesis agent then uses this specification to drive implementation. This decomposition resolves documentation ambiguities before coding begins and provides a stable behavioral reference throughout synthesis. We evaluate SpecFirst on all 200 ProgramBench instances across four models spanning two families and an order of magnitude of capability. SpecFirst consistently outperforms the single-loop baseline, improving test pass rates by 6.9%-21.3% and binary exploration coverage by 9.4%-18.5%, all statistically significant. Behavioral analysis on code synthesis further shows that a prior specification enables earlier and more sustained code construction. Our results demonstrate that an explicit requirements-engineering phase is an effective paradigm for from-scratch program construction.

MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis

Coding agents have made substantial progress on software engineering tasks that modify existing codebases, including bug fixing and feature implementation. However, constructing a complete program from scratch remains a major challenge: even the frontier models evaluated on ProgramBench fully resolve fewer than 1% of tasks. One obstacle is the lack of scalable training environments for this from-scratch setting, spanning the whole software engineering life cycle, as existing environment-construction frameworks focus only on a single phase in software development. To address this gap, we introduce MindForge, an automated pipeline that converts open-source command-line programs into source-free environments that expose only a compiled reference executable and its documentation. Using MindForge, we construct training environments from repositories disjoint from those in ProgramBench, and curate a high-quality data recipe consisting of program synthesis trajectories using GLM-5.2 as the teacher agent. Fine-tuning Qwen3.6-27B on these trajectories increases its ProgramBench average test pass rate from 37.98% to 49.51%, achieving performance comparable to substantially larger frontier models. Moreover, the fine-tuned model consistently improves over the base model across all seven unseen software engineering benchmarks, spanning long-horizon repository generation and translation, bug fixing, feature implementation, and cross-language issue resolution, with absolute gains of 31.00 points on RepoZero-C2Rust, 14.16 on DeepSWE, 10.70/4.56 on NL2Repo-Bench (with/without tests), 5.04 on SWE-bench Verified, 5.93 on SWE-bench Pro, 5.22 on SWE-bench Multilingual, and 4.94 on FeatBench.

Agentic Synthesis against Counterexample-Supplemented Sketches

Coding agents can fix a failing example without preserving the domain rule that made it fail. We present agentic synthesis against counterexample-supplemented sketches, a repository-native method for systems whose policy is discovered during implementation. A human starts with a partial sketch, and a coding agent compiles a replaceable projection. When simulation exposes missing or mistaken policy, an operator approves the corrected behavior and the minimum general rule the case authorizes. Every Developer call names its change authority and the rules, holes, anchors, and approved behavior that must survive. Conflict or ambiguous permission leaves the files unchanged and produces a clarification question. A complete archive preserves provenance; a curated regression set gates distinct boundaries. Before another candidate is revealed, the active case and curated regressions must pass both deterministic approved-output comparison and a separate review against the current sketch. Periodic clean regeneration tests whether the sketch carries the learned policy. We demonstrate the method with CatSynth, a captured synthetic application. In one open-world run with GPT-5.4-mini, 8 of 14 frozen candidates became counterexamples. Under the corrected protocol, replay-all, evolved-sketch rebuild, and retained Sketch-CE each passed all 8 accepted cases. They passed 14, 17, and 16 of 21 withheld cases, respectively. Sketch review rejected premature empty-input and tag policies and restored dropped anchors; adjudicated reviewer errors did not become policy. One model and one reveal order cannot establish general correctness or superiority. On this suite, the second check exposed drift hidden by deterministic replay, and the reviewed sketch passed three more withheld cases than raw example replay.

Formal Disco: Scalable Open-Ended Generation of Formally Verified Programs

The cost of producing code is rapidly diminishing with increasingly capable AI agents, while quality assurance of generated programs has not kept pace. Formal verification provides the strongest possible guarantees, but the ability of AI models to work with verification-aware languages is hindered by the scarcity of human-written examples of programs in those languages. To tackle this prevalent data scarcity issue, we propose Formal Disco: a distributed system for coordination of LLM-based workers that can be easily applied to open-ended synthetic data generation at scale. We use Formal Disco to share tasks and programs between three classes of workers: "initiators", which read random READMEs from open-source repositories and documentation snippets to sketch a related verified program, "fixers" which take compiler and verifier feedback and attempt to resolve issues, and "extenders" that take working programs and propose patches to expand them. Formal Disco records all agent-generated traces and uses them both for initial distillation from a stronger model as well as self-improvement. We also propose a principle of maximum entropy for synthetic program generation, and use entropy maximization via iterative supervised fine-tuning to learn to generate increasingly diverse programs over time. We release large datasets of synthetic verified programs in three languages - Dafny, Verus, and Frama-C -, and fine-tune open models for verification-relevant tasks, often matching or exceeding the performance of Claude Opus 4.5. Overall, our work offers a path to create synthetic data at scale for formal reasoning domains and overcome the long-standing data barrier.

RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments

For most of scientific history, researchers studying behavior could only infer hidden mechanisms from outward actions: an inverse problem that becomes more tractable when observation is augmented by targeted intervention. We pose a computational analogue: given only behavioral traces of an agent in a game environment, can a learner reconstruct the underlying decision program as executable code, and how much does this reconstruction improve with the ability to design controlled experiments? We introduce RevengeBench, a benchmark of 75 LLM generated, Elo-calibrated policies across five game environments, drawn from CodeClash tournament trajectories. The learner observes the hidden target policy play against sampled opponents and designs behavioral probes in the form of custom opponent policies that elicit informative behavior. It then submits an executable hypothesis, which is evaluated using continuous action-distance metrics. We further validate that recovered code carries informative signal in downstream player-versus-player tournaments. Across twelve frontier LLMs, recovery quality varies substantially (34 to 72% of initial distance closed), with reconstructed policies yielding measurable competitive advantage, particularly for weaker models that otherwise struggle to design effective counter-strategies. Our benchmark positions behavioral recovery of programmatic policies as a tractable inverse problem in code-space, opening a path to opponent modeling, policy interpretability, and the broader question of inferring latent mechanisms from observations.

ANCORA: Learning to Question via Manifold-Anchored Self-Play for Verifiable Reasoning

We propose a paradigm shift from learning to answer to learning to question: can a language model generate verifiable problems, solve them, and turn the resulting feedback into self-improvement without human supervision? We introduce ANCORA, an anchored-curriculum framework in which a unified policy alternates between a Proposer that synthesizes novel specifications and a Solver that produces verified solutions. ANCORA rests on three load-bearing mechanisms: a two-level group-relative update that couples Proposer advantages across specifications with Solver advantages across solution attempts; iterative self-distilled SFT that projects the base model onto its valid-output manifold before RL; and a UCB-guided Curriculum DAG that grows only through strictly filtered, novel, Solver-verified specifications. These stabilizers are necessary because sparse verifier feedback otherwise drives Proposer collapse even under MLRL-aligned rewards. Instantiated in Verus, ANCORA lifts Dafny2Verus pass@1 from a 26.6% SFT baseline to 81.5% in the test-time-training setting under 0-shot evaluation, outperforming the PSV self-play baseline by 15.8 points despite PSV using 1-shot inference; in a separate transfer setting, training from Dafny2Verus seeds yields 36.2% and 17.2% pass@1 on held-out MBPP and HumanEval.

Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis

Large-scale transformers achieve impressive results on program synthesis benchmarks, yet their true generalization capabilities remain obscured by data contamination and opaque training corpora. To rigorously assess whether models are truly generalizing or merely retrieving memorized templates, we introduce a strictly controlled program synthesis environment based on a domain-specific arithmetic grammar. By systematically enumerating and evaluating millions of unique programs, we construct interpretable syntactic and semantic metric spaces. This allows us to precisely map data distributions and sample train and test splits that isolate specific distributional shifts. Our experiments demonstrate that optimizing density generalization -- through diverse sampling over both semantic and syntactic spaces -- induces robust out-of-distribution generalization. Conversely, evaluating support generalization reveals that transformers severely struggle with extrapolation, experiencing a performance drop of over 30% when forced to generate syntactically novel programs. While steadily scaling up compute improves generalization, the gains follow a strictly log-linear relationship. We conclude that robust generalization requires maximizing training diversity across multiple manifolds, and our findings indicate the necessity for novel search-based approaches to break through current log-linear scaling bottlenecks.