ICML 2026 Papers

Rich-format documents are essential for everyday operations yet costly to author, motivating the need for automated generation to enhance productivity. To this end, we present FormAct, an agentic system that generates professional rich-format documents from scratch. FormAct operates on an HTML source representation and performs iterative source refinement with an *editing agent* that invokes a suite of tools, including a syntax-aware source editor and a template retriever, and a *review agent* that critiques rendered pages to guide refinement. Additionally, we incorporate edit-triggered context compression to maintain a bounded working context and keep multi-round editing efficient. To support development and evaluation, we introduce RichDocBench for end-to-end generation, and RichDocFuzz to evaluate formatting-error recognition for reviewer agents. Through extensive automated evaluation and blind human-preference studies, we show that FormAct consistently outperforms strong baselines, including Codex-CLI, with particularly strong improvements in generating error-free, professional rich-format documents.

Time series generation (TSG) is widely used across domains, yet most existing methods assume regular sampling and fixed output resolutions. These assumptions are often violated in practice, where observations are irregular and sparse, while downstream applications require continuous and high-resolution TS. Although Neural Controlled Differential Equation (NCDE) is promising for modeling irregular TS, it is constrained by a single dynamics function, tightly coupled optimization, and limited ability to adapt learned dynamics to newly generated samples from the generative model. We propose Diff-MN, a continuous TSG framework that enhances NCDE with a Mixture-of-Experts (MoE) dynamics function and a decoupled architectural design for dynamics-focused training. To further enable NCDE to generalize to newly generated samples, Diff-MN employs a diffusion model to parameterize the NCDE temporal dynamics parameters (MoE weights), i.e., jointly learn the distribution of TS data and MoE weights. This design allows sample-specific NCDE parameters to be generated for continuous TS generation. Experiments on ten public and synthetic datasets demonstrate that Diff-MN consistently outperforms strong baselines on both irregular-to-regular and irregular-to-continuous TSG tasks. The code is available at the link \url{https://github.com/microsoft/TimeCraft/tree/main/Diff-MN}.

Designing genetic circuits, which are biological systems capable of programmed behaviors within living cells, remains a laborious, expert-driven process despite decades of progress in synthetic biology. We introduce GenCircuit-RL, a reinforcement learning framework that trains language models to reason about genetic circuit design through code generation, where models produce Python code using PySBOL to construct circuits in the standardized Synthetic Biology Open Language (SBOL) format. Our approach addresses the challenge of sparse feedback in biological design through hierarchical verification rewards that decompose correctness into five levels, from code execution through structural validity to functional behavior, providing dense learning signal while multiplicative dependencies prevent reward hacking. We contribute SynBio-Reason, a benchmark of approximately 4,753 circuits spanning six canonical circuit types and nine tasks from code repair to de novo design, with held-out biological parts enabling rigorous out-of-distribution evaluation. A four-stage curriculum progressively shifts optimization pressure from basic code generation toward functional correctness, enabling models to acquire compositional reasoning capabilities incrementally. Our framework demonstrates that hierarchical verification combined with curriculum learning enables compact language models to generate functionally correct genetic circuits, including generalization to novel biological parts and rediscovery of canonical designs from synthetic biology literature.

Vericoding refers to the generation of formally verified code from rigorous specifications. Recent AI models show promise in vericoding, but a unified methodology for cross-paradigm evaluation is lacking. Existing benchmarks test only an individual language/tool (e.g., Dafny, Verus, and Lean) and each covers very different tasks, so the performance numbers are not directly comparable. We address this gap with AlgoVeri, a benchmark that evaluates vericoding of $77$ classical algorithms in each of Dafny, Verus, and Lean. By enforcing identical functional contracts, AlgoVeri reveals critical capability gaps in current models. While frontier models achieve tractable success in Dafny ($40.3$\% for Gemini-3 Flash), where high-level abstractions and SMT automation simplify the workflow, performance collapses under the systems-level memory constraints of Verus ($24.7$\%) and the explicit proof construction required by Lean ($7.8$\%). Beyond aggregate metrics, we uncover a sharp divergence in test-time compute dynamics: Gemini-3 effectively utilizes iterative repair to boost performance (e.g., tripling pass rates in Dafny), whereas GPT-OSS saturates early. Finally, our error analysis shows that language design affects the refinement trajectory: while Dafny allows models to focus on logical correctness, Verus and Lean trap models in persistent syntactic and semantic barriers.

Despite recent progress, recovering parametric CAD construction sequences from geometric input, such as meshes or point clouds, is a key challenge for design and manufacturing, as existing CAD reconstruction and generation methods are largely restricted to difficult-to-edit formats like meshes or Breps or editable simple sketch-and-extrude pipelines and low-complexity datasets. We introduce CADFit, a hybrid optimization-based CAD reconstruction framework that recovers complex, editable CAD construction sequences from meshes by incrementally fitting and validating parametric operations using geometric feedback. Our approach is distinguished by formulating reconstruction as an IoU-driven optimization over structured CAD programs and supporting a rich set of operations, including extrusions, revolutions, fillets, and chamfers. Experiments on multiple CAD benchmarks show that CADFit outperforms state-of-the-art mesh-to-CAD methods in volumetric Intersection-over-Union and Chamfer Distance, while substantially reducing the Invalid Ratio of reconstructed CAD programs, particularly for complex designs. We further present a multimodal pipeline that enables end-to-end reconstruction of CAD construction sequences from images by combining image-based geometry reconstruction with CADFit. By enabling accurate reconstruction of higher-complexity CAD models, CADFit provides a practical foundation for generating richer datasets and advancing future learning-based approaches to CAD reverse engineering. The code is available at: https://github.com/ghadinehme/CADFit.

The rapid evolution of Large Language Models (LLMs) has empowered even non-programmers to create visually appealing frontend mini-games with a single instruction. However, open-source models significantly lag behind proprietary counterparts in this domain. The core bottleneck is the lack of an evaluation mechanism that balances reliability with scalability, as existing methods either fail to verify dynamic interactivity or incur prohibitive computational costs. To bridge this gap, we introduce ALIVE (Aligning LLMs via Interactive Visual Execution), a high-throughput framework that leverages one-shot planning and DOM-based analysis to automatically evaluate generated games at scale. Extensive experiments demonstrate that ALIVE significantly outperforms static judge baselines in identifying functional flaws while remaining orders of magnitude more efficient than GUI agents. Functioning as a scalable `pre-flight' evaluation layer, it curates high-quality data for Supervised Fine-Tuning (SFT) and provides a consistent reward signal for Reinforcement Learning (RL). We leverage this pipeline to train ALIVE-Coder, a model achieving superior performance in interactive frontend generation. To the best of our knowledge, our work offers the first scalable path to evaluate and optimize interactive code, substantially advancing open-source capabilities.

Diffusion-based large language models (dLLMs) have emerged as a promising alternative to autoregressive models, leveraging simultaneous denoising to enable global planning and iterative refinement. These properties make dLLMs attractive for long-context generation. However, deploying dLLMs faces a prohibitive memory barrier, as existing inference systems are inefficient for the diffusion paradigm. We observe that current inference systems are misaligned with dLLMs. Unlike autoregressive models, whose memory footprint is dominated by the KV-Cache, dLLMs are bottlenecked by transient activations rematerialized per step. Moreover, generic memory reuse mechanisms lack the global visibility to handle dynamic memory peaks of dLLMs, which alternate between logits and feed-forward networks. To address these challenges, we present Mosaic, a memory-efficient inference system that shifts dLLM execution from local, static management to a global, dynamic paradigm. Mosaic integrates (i) a mask-only logits kernel eliminating redundant activation materialization, (ii) a lazy chunking optimizer using online heuristics to tame dynamic memory peaks, and (iii) a global memory manager leveraging virtual addressing to mitigate memory fragmentation. Evaluations show that Mosaic reduces the memory peak-to-average ratio by 2.71$\times$ on average and increases the maximum inference sequence length on identical hardware by 15.30--32.34$\times$. Crucially, Mosaic is training-free and preserves exact model outputs, while reducing end-to-end latency by 2.5\%--55.4\%. Our code is publicly available at https://github.com/flashserve/Mosaic.

Asynchronous reinforcement learning has become increasingly central to scaling LLM post-training, delivering major throughput gains by decoupling rollout generation from policy updates. However, widely used policy-gradient objectives such as REINFORCE and GRPO suffer under high asynchrony: stale rollouts produce heavy-tailed importance weights, so a small number of trajectories dominate updates and the policy-gradient estimator becomes **markedly higher variance**. Through systematic analysis on math, reasoning, and tool-use benchmarks, we establish that this increasing variance is reliably predicted by collapsing effective sample size (ESS), which prior stabilization methods largely fail to address. Motivated by this diagnosis, we introduce **V**ariance **C**ontrolled **P**olicy **O**ptimization (VCPO), a method that (i) dynamically scales the learning rate with ESS to dampen unreliable updates and (ii) applies a closed-form minimum-variance baseline for off-policy settings, without a critic model and adding minimal overhead. Empirically, across math and general reasoning benchmarks, this enables robustly stable asynchronous training compared to previous stabilization and algorithmic methods, even in highly off-policy regimes (128 steps off-policy). In a long-horizon, tool-use task, VCPO matches synchronous performance while delivering a 2.5× speedup in training time. Code is available at: https://github.com/mit-han-lab/vcpo

Code repair is an important capability for language models (LMs): given a buggy program and unit tests, an LM must produce a fixed program that passes the tests. We aim to scale supervision for code repair by having an LM generate bug--fix tasks with unconstrained edits, using unit tests as the only verifier. We propose generator-fixer self-play, in which a single model is trained with reinforcement learning to alternate between generating bugs and fixing them. As the fixer improves, the generator adapts to produce increasingly difficult bugs, yielding an automatic curriculum. However, because unit tests certify correctness but not realism, we find that the generator can drift from bugs encountered in practice, improving repair on self-generated bugs while degrading on real-world bugs. We propose Anchored Self Play (ASP), which anchors self-play with a small reference set by (i) adding a code-embedding similarity reward to guide generation and (ii) mixing reference bugs into fixer training to prevent drift. To reflect LM-assisted programming, where bugs come from humans, LMs, and human edits of LM code, we introduce BugSourceBench, a code repair benchmark spanning human-authored bugs, human-edited buggy LM code, and errors in LM-generated code. Across bug sources, ASP achieves the best fix rates, improving average fix rate by $+25$% (relative) / $+7.2$ pp (absolute) over standard self-play, with gains on both LM-error bugs ($+100$% relative / $+11$ pp absolute) and human-authored bugs ($+7.1$% relative / $+3.4$ pp absolute).

We investigate language generation in the limit (Kleinberg & Mullainathan, 2024; Li et al., 2025) in variants where the generator receives some feedback based on its “actions.” We study two such variants. In the first, which is inspired by Littlestone’s model of online learning, the generator observes whether it made a mistake at each iteration. In the second, introduced by Charikar & Pabbaraju (2025a), the generator can query whether a string belongs to the target language. Our main result is a characterization of collections that are generable with mistake feedback. Using similar techniques, we also characterize when generation is possible in the query model with set-based generators; set-based generators have been studied in several works (Charikar & Pabbaraju, 2025a; Kalavasis et al., 2025; Kleinberg & Wei, 2025a; Li et al., 2025). Beyond the characterizations themselves, we derive several implications. First, our results imply new closure properties for generation with mistake and query feedback. Second, our results show that, under feedback, generation is robust to noise: it remains possible with arbitrary contamination in the adversary’s examples and with finite contamination in the feedback. Third, our techniques also yield new sufficient and necessary conditions for generation without feedback among other implications.

The field of Computer-Aided Design (CAD) generation has made significant progress in recent years. Existing methods typically fall into two separate categories: parametric CAD modeling and direct boundary representation (B-Rep) synthesis. In modern feature-based CAD systems, parametric modeling and B-Rep are inherently intertwined, as advanced parametric operations (e.g., *fillet* and *chamfer*) require explicit selection of B-Rep geometric primitives, and the B-Rep itself is derived from parametric operations. Consequently, this paradigm gap remains a critical factor limiting AI-driven CAD modeling for complex industrial product design. This paper presents *FutureCAD*, a novel text-to-CAD framework that leverages large language models (LLMs) and a B-Rep grounding transformer (*BRepGround*) for high-fidelity CAD generation. Our method generates executable CadQuery scripts, and introduces a text-based query mechanism that enables the LLM to specify geometric selections via natural language, which *BRepGround* then grounds to the target primitives. To train our framework, we construct a new dataset comprising real-world CAD models. For the LLM, we apply supervised fine-tuning (SFT) to establish fundamental CAD generation capabilities, followed by reinforcement learning (RL) to improve generalization. Experiments show that *FutureCAD* achieves state-of-the-art CAD generation performance. Code and dataset are available at https://github.com/JohanStackk/FutureCAD.

The insatiable demand for web-scale training data has exposed LLMs to a subtle but consequential threat: the absorption of malicious scam content into model weights and its subsequent reproduction during inference. In November 2024, this risk materialized when a developer reportedly lost 2,500 USD after ChatGPT generated an otherwise routine cryptocurrency trading script containing a live phishing URL. To systematically investigate this problem, we introduce Scam2Prompt, an automated auditing framework that crawls known scam websites, infers their functional intent, and synthesizes innocuous developer-style prompts — the kind of legitimate coding requests a programmer might naturally submit — to evaluate whether LLMs reproduce the underlying scam endpoints. Importantly, our approach requires neither jailbreaking nor adversarial prompting; all 1,377 prompts in our benchmark, Innoc2Scam-bench, which is automatically constructed by Scam2Prompt, were human-validated as benign coding tasks. Evaluation of seven production LLMs released in 2025 on Innoc2Scam-bench shows that the vulnerability proves both persistent and severe: malicious code generation rates range from 12.9% to 47.3% across the evaluated models, and no tested model proves immune. State-of-the-art guardrails and RAG-based agents offer only limited protection, underscoring an urgent need for explicit URL validation in LLM-assisted software development pipelines.

Autoregressive (AR) models have shown great promise in image generation, yet they face a fundamental inefficiency stemming from their core component: a vast, unstructured vocabulary of visual tokens. By treating tokens as a flat set, standard models overlook the manifold structure where geometric proximity reflects semantic similarity. This oversight unnecessarily complicates the prediction task, hindering training efficiency and limiting generation quality. To resolve this, we propose Manifold-Aligned Semantic Clustering (MASC), a principled framework that constructs a hierarchical semantic tree directly from the codebook's intrinsic geometry. Utilizing a geometry-aware distance metric and density-driven agglomerative construction, MASC faithfully models the token embedding manifold. By transforming the flat, high-dimensional prediction into a structured hierarchical task, MASC introduces a powerful inductive bias that simplifies learning. Designed as a plug-and-play module, MASC accelerates training by up to 71\% and significantly boosts generation quality, improving LlamaGen-XL's FID from 2.87 to 2.49. Crucially, MASC further serves as a convergence enabler for complex architectures. These results establish that structuring the prediction space is as vital as architectural innovation, elevating existing AR frameworks to state-of-the-art performance.

Hallucination is a central limitation of large language models (LLMs), and substantial effort has been devoted to understanding and mitigating it. Towards this, Kalai and Vempala (STOC 2024) introduced a probabilistic framework formalizing calibration and hallucination, and showed that, with high probability, calibrated LLMs hallucinate roughly at the rate of the "missing mass", a measure of how incomplete the training data is relative to its source. This raises two fundamental questions: (i) what property of a calibrated LLM makes hallucinations unavoidable? and (ii) can hallucinations be avoided by giving up calibration? We answer these questions by introducing a simpler property we call *innovation* that measures the tendency of a model to produce outputs outside the training data. We show that innovation is implied by the condition for hallucination identified by Kalai and Vempala, and, further, that it is an almost characterization of hallucination: hallucination implies innovation, and conversely, innovation implies hallucination with high probability. We also provide lower bounds on the hallucination rate based on the "innovation rate", and by relating innovation rate back to missing mass, we obtain new hallucination rate lower bounds based on missing mass that extend the results of Kalai and Vempala.

Developing effective representations for register transfer level (RTL) designs is crucial for accelerating the hardware design workflow. Existing approaches, however, typically rely on a single data modality, either the RTL code or its associated graph-based representation, limiting the expressiveness and generalization ability of the learned representations. For RTL, the control data flow graph (CDFG) offers a comprehensive structural representation that preserves complete information, while the code modality explicitly encodes semantic and functional information. We argue that integrating these complementary modalities is essential for a thorough understanding of RTL designs. To this end, we propose UniRTL, a multimodal pretraining framework that learns unified RTL representations by jointly leveraging code and CDFG. UniRTL achieves fine-grained alignment between code and graph through mutual masked modeling and employs a hierarchical training strategy that incorporates a pretrained graph-aware tokenizer and staged alignment of text (*i.e.*, functional summary) and code prior to graph integration. We evaluate UniRTL on two downstream tasks, performance prediction and code retrieval, under multiple settings. Experimental results show that UniRTL consistently outperforms prior methods, establishing it as a more robust and powerful foundation for advancing hardware design automation.

Parametric CAD is widely used in mechanical and product engineering, but current generative models still have difficulty producing assemblies that are both editable at the parameter level and consistent with inter-part constraints. Methods that generate meshes or history-free B-rep can represent multi-part shape, but they often lack the program structure and constraint logic needed for reliable downstream edits; in contrast, code-based CAD generation offers direct parametric control, yet most published settings and evaluations focus on single-part solids rather than constrained assemblies. We introduce SPADA (Self-testing Parametric Assembly Design Agent), a test-driven agent that synthesizes assembly code together with deterministic verification tests, and uses these tests as an executable contract for controllable generation. SPADA runs an iterative compile-test-repair loop with multimodal feedback, checking both specification logic and physical feasibility through programmatic constraints. To support evaluation, we release SPADA-Bench-Verified, a human-validated benchmark of real-world code-centric assemblies paired with deterministic tests and engineering-style constraints. Experiments show that SPADA could produces complex assemblies while maintaining geometric fidelity, supporting test-driven agents as a concrete path toward reliable, controllable CAD generation.

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models, offering sub-linear generation latency and bidirectional capabilities that are particularly appealing for code generation and editing. Achieving sub-linear latency in discrete DLMs requires predicting multiple tokens in parallel. However, standard DLMs sample tokens independently from conditional marginal distributions, failing to capture the joint dependencies among concurrently generated tokens. As a result, they often lead to syntactic inconsistencies and break multi-token structures. In this work, we introduce CoDiLA (Coherent Diffusion with Local Autoregression), a method that reconciles parallel sampling with local dependency modeling. Rather than forcing the DLM to resolve fine-grained syntax, CoDiLA delegates local decoding to a small, auxiliary AR model operating on the diffusion latents. This design allows for parallel generation while ensuring sequential validity within a block and maintaining core DLM capabilities, including bidirectional modeling across blocks. We demonstrate that using a highly compact auxiliary AR model (e.g., 0.6B parameters) effectively eliminates coherence artifacts, establishing a new Pareto frontier for accuracy and speed in code generation benchmarks.

Code-writing large language models (CodeLLMs) generate executable code policies for embodied agents by translating natural language goals and environmental constraints into structured control programs. However, policy generation in open-domain embodied environments suffers from two fundamental limitations: (i) delayed decoding caused by repetitive prefill computation over long prompts, and (ii) limited robustness due to fully generative decoding, which often produces API mismatches, missing safety guards, and unstable control logic. To address these limitations, we present FCGraft, a Functional Cache Grafting framework. FCGraft maintains a library of function-level validated code skeletons and their associated prompt-level Transformer key–value (KV) caches, and synthesizes new policies by retrieving relevant functions and grafting their KV caches when a new task is provided. Given retrieved function caches, FCGraft performs cache grafting via stitching, which composes cached function segments into a composite policy, and patching, which locally adapts only the necessary code regions to satisfy task-specific parameters and constraints with minimal additional decoding. By eliminating redundant prefill computation, this approach reduces generation latency, while reusing validated control structures improves robustness over prompt-level caching methods RAGCache, achieving $18.31\$% higher task success rate and $2.3\times$ faster policy synthesis.

Large language models (LLMs) are increasingly used to generate executable outputs, JSON objects, and API calls, where a single syntax error can make the output unusable. Constrained decoding enforces validity token-by-token via masking and renormalization, but it can distort generation when the model assigns low probability mass to valid continuations, pushing decoding toward locally valid yet semantically incorrect trajectories. We propose \emph{Draft-Conditioned Constrained Decoding (DCCD)}, a simple two-step, training-free inference procedure that decouples semantic planning from structural enforcement: an unconstrained draft is generated first, and constrained decoding is then applied, conditioned on this draft, to guarantee validity. We analyze DCCD through a KL-projection view, showing that draft conditioning increases feasible mass and reduces the cumulative “projection tax” induced by hard constraints, with an optional best-of-$K$ draft selection. Across structured reasoning benchmarks, DCCD improves strict structured accuracy by up to +24 percentage points over standard constrained decoding (e.g., 15.2\% to 39.0\% on GSM8K with a 1B model), and enables smaller model pairs to match or exceed much larger constrained baselines, yielding substantial gains in parameter efficiency.