LLM-Based Program Synthesis

Follow this topic Ask about this topic

Momentum

22 papers in the last four weeks, up 100% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 223

Oct 7, 2026cs.LG

EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control Programs

Effective traffic signal control (TSC) requires policies that respond to changing traffic demand and network conditions while meeting different control objectives. However, adapting existing strategies often involves repeated manual design and adjustment, making it difficult to systematically explore better control rules for a target network. Large language models (LLMs) can automate this process, but directly using them to select signal phases leaves decision rules embedded in black-box models and incurs recurring inference costs and latency. This paper formulates TSC as a modular program design problem and proposes EvoSignal, an LLM-guided evolutionary framework using traffic knowledge and performance feedback. The modular representation separates traffic feature extraction, local phase prioritization, and optional network-based priority adjustment. Starting from several established strategies, EvoSignal improves programs through feedback on congestion and signal operation, retaining strategies with different performance trade-offs. The resulting programs operate without online LLM inference. Simulation experiments across five scenarios on two real-world road networks show that the selected default EvoSignal program reduces waiting time by 16.8--49.2% relative to the lowest waiting time achieved by the 20 conventional, reinforcement learning-based, and LLM-based baselines in each scenario. A program prioritizing travel time and queue length outperforms all 20 baselines on all three metrics in the search scenario and remains among the top three on each metric when transferred unchanged to the other four scenarios. These findings support automated design of inspectable control programs that transfer across the evaluated road networks and traffic demands.Code is available at https://github.com/georgewanglz2019/EvoSignal.

Leizhen Wang, Peibo Duan, Zhenlin Qin +5

Monash University · KTH Royal Institute of Technology · Chinese Academy of Sciences +2

Traffic Signal Control Automated Heuristic Design LLM-Based Program Synthesis Program Synthesis Evolutionary Optimization

Oct 6, 2026cs.AI

AGAR: a reinforcement learning substrate for LLM program evolution

Given a task and an evaluator, a language model can rewrite a candidate program while a search loop decides which rewrites survive, offering a practical route to algorithm discovery. But that loop is governed by five constants set by hand: which parent to select, how hard to mutate, how to keep diversity, what to remember, and a scalar score that never says which part of the program earned it. Reinforcement learning already has an estimator for each. The obstacle is that program evolution is not usually written down as a decision process. We formalize it as a Markov decision process whose action is the modular prefix the model is conditioned on, rather than the program it emits. Credit assignment, value estimation, adaptive exploration, and experience memory can then attach to distinct components. AGAR (Algorithm Generation As RL) provides the resulting substrate: any estimator can be replaced or switched off without changing the controller, making the transfer auditable one mechanism at a time, with no gradient training of the backend model. Across 19 tasks, two backends, and three seeds under one harness, AGAR improves on the stronger of two published baselines on most tasks, with gains concentrated in the competitive-programming family. The formalization also yields a checkable reading of prior work: these systems are implicitly zero-discount, not by choice, but because fitness is exogenous to an individual rather than a return over successors, leaving a discount factor nothing to act on.

Haoran Li, Zengle Ge, Xiaomin Yuan +11

University of the Chinese Academy of Sciences · Baidu · Tsinghua University +2

LLM-Based Program Synthesis RL for Code Generation Reinforcement Learning Credit Assignment in RL

Oct 6, 2026cs.AR

CACHEFORGE: LLM-Guided End-to-End Generative Cache Replacement Policy for Performance and Hardware Efficiency

Modern cache replacement designs saturate because they operate within fixed representational structures, hand-crafted and heuristic based feature-engineered predictors, or offline imitation models that cannot generate new decision logic on their own. At the same time, replacement is shaped by the causal interaction of prefetching, thrashing, spatial locality, and access-type behavior, producing an enormous design space that is difficult to traverse manually. Prior approaches typically rely on heuristics, parameter tuning, or imitation of an offline optimal policy, capturing correlations rather than synthesizing new mechanisms. As a result, their performance gains often plateau and they overfit under dynamic workload conditions. CACHEFORGE is the first framework to evolve cache-replacement policies end-to-end by embedding a large language model inside a governed hardware-aware loop. In each iteration, the LLM proposes new C++ replacement logic, the policy is evaluated under a trace-based CRC-2 ChampSim simulator, and the framework enforces feasibility through reward shaping, structural checks, dynamic mutation, temperature scheduling, and cross-policy crossover. This closed-loop generation-evolution loop specifically designed for cache replacement policy enables the discovery of compact policies that satisfy hardware constraints while exploring algorithmic transformations beyond fixed predictor structures. Across SPEC CPU2006, CACHEFORGE outperforms all CRC-2 baselines. It improves the total hit rate by 27.36%, 19.69%, 13.72%, 13.15%, 11.83%, and 5.73% over MPPPB, ReD, Hawk-eye, SHiP++, LIME, and LRU, respectively. On memory-intensive workloads, it increases IPC by 10.15%, 7.89%, 6.34%, 3.64%, 3.12%, and 2.71% over LRU, MPPPB, LIME, ReD, SHiP++, and Hawkeye.

Kaushal Mhapsekar, Bita Aslrousta, Brijesh Kumar Bhayana +5

Department of Electrical and Computer Engineering North Carolina State University, Raleigh, NC, USA

Large Language Model-Guided Optimization LLM-Based Program Synthesis

Oct 5, 2026cs.LG

SimAuthor: Harnessing Foundation Models for Persistent Scientific Simulator Authoring

Foundation models can generate scientific code, but authoring a scientific simulator (an executable program encoding hypotheses about how mechanisms generate observable signals) requires iterative refinement. Scientific adequacy rarely admits a unique implementation or exact test, so simulators must instead be judged against limited real observations. We study this setting as scientific simulator authoring under weak empirical feedback, where distributional comparisons between simulated and real signals guide revision, and the target is the simulator itself rather than only its generated samples. We introduce SimAuthor, a persistent authoring harness that retains and revises executable simulators, separates scalar search scores from structured discrepancy feedback, and accumulates reusable implementation mechanisms. We evaluate SimAuthor on six biomedical tasks spanning cardiac and respiratory audio, photoplethysmography (PPG), and electrocardiography (ECG). Under a fixed 100-attempt budget, SimAuthor outperforms PUCT score search on all six tasks, generally outperforms textual-strategy optimization, and achieves the highest endpoint score on five of six. The authored simulators also improve on unseen recordings, transfer to independent pretrained representations, and yield substantial out-of-distribution gains in downstream ECG classification. Finally, 111 of 138 audited revisions alter program structure and account for 86.1% of the signed score improvement. These results suggest that persistent revision can progressively convert foundation-model knowledge into better executable scientific simulators from limited empirical evidence.

Yishan Wang, Ran Piao, Mathias Funk +1

Eindhoven University of Technology

LLM-Based Program Synthesis Scientific Code Generation

Oct 1, 2026cs.LG

Have an LLM Write Your Anomaly Detector: Autonomous Discovery of Compact, Interpretable Detectors for Time Series

Time-series anomaly detection trades off predictive accuracy, computational efficiency, and interpretability. We use a large language model not as the detector but as the author of one: an autonomous research loop in which the model repeatedly edits a single short NumPy program under a leakage-free objective, keeping the best-scoring detector it finds. The loop discovers two compact detectors, one for univariate and one for multivariate series, that describe short windows by their local spectral features and compare them with the training-region distribution through a covariance-aware distance. On the TSB-AD benchmark these detectors lead the field across metrics, ahead of the strongest classical, deep, and foundation-model baselines including Time-RCD, yet they train no network and use no GPU, and the multivariate detector is faster than every similarly performing baseline. LLM-driven program search is thus a practical route to accurate, efficient, and transparent detectors.

David Berghaus

Lamarr Institute Germany · Fraunhofer IAIS Germany

Interpretable Anomaly Detection LLM-Based Program Synthesis Unsupervised Anomaly Detection Time-Series Anomaly Detection Anomaly Detection

Oct 1, 2026cs.DB

HakiCC: LLM-Driven Multi-Agent Design and Optimization of Concurrency Control Protocols

Large language models (LLMs) have recently been applied in systems research as a tool to reduce human-intensive engineering effort through cost-efficient automation. Decades of research have produced a rich landscape of concurrency control (CC) protocols, each encoding distinct trade-offs in correctness, throughput, and abort behavior. However, most applications in practice default to 2PL or OCC, because selecting and adapting a protocol to a specific application requires expert knowledge that is rarely available to application designers. This is a wasted opportunity, as an application-specific CC protocol can yield significant performance advantages over a generic baseline, but designing one requires deep expertise in CC protocol design. In this paper, we propose HakiCC, an LLM-driven multi-agent pipeline that automatically designs, verifies, and optimizes concurrency control protocols tailored to a given target application. HakiCC provides a two-stage pipeline. In Stage 1, a multi-agent system takes a workload description as input and generates an application-specific CC protocol implementation, which is iteratively repaired and verified for conflict-serializability. In Stage 2, the verified protocol is further optimized for that application through an LLM-driven evolutionary loop targeting correctness and throughput. We evaluate HakiCC on TPC-C and AuctionMark as target workloads, producing and reporting ten application-specific CC protocols. All ten are conflict-serializable after Stage 1; Stage 2 improves throughput for every protocol, with average gains of +50.6% for TPC-C protocols and +92.2% for AuctionMark protocols.

Farzad Habibi, Juncheng Fang, Faisal Nawab

University of California, Irvine

Large Language Model-Guided Optimization LLM-Based Program Synthesis

Sep 30, 2026cs.LG

LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery

Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evidence from other experiments, whereas including the full experimental history produces long, redundant contexts. We introduce a simple, single-agent discovery harness built around LabBook, an agent-maintained memory that serves two complementary roles: guiding retrieval of relevant evidence from a complete experimental log and informing the generation of new solutions. At each iteration, the same agent combines its memory with retrieved evidence and jointly produces the next program and an updated LabBook. This separates complete history retention from selective context construction, without requiring an explicit population or branching search structure. On 49 Frontier-CS problems, LabBook improves the observed quality-cost trade-off over the evaluated evolutionary baselines with two backbones, while remaining competitive across nine additional mathematical, systems, and heuristic-design tasks. Code will be released at https://github.com/BoYuanVisionary/LabBook.

Bo Yuan, Wenqian Ye, Zelin Zhao +4

Georgia Institute of Technology · University of Virginia, Charlottesville

Automated Algorithm Discovery LLM-Based Program Synthesis Large Language Model-Guided Scientific Discovery Memory-Augmented Language Model Agents

Sep 30, 2026cs.CV

MatLoom: Layered Text-to-Material Generation in a Compact Program Space

Material generation should produce not only an appearance, but also the rules that construct it. We introduce MatLoom, a compact, layer-oriented language for text-to-material generation with pretrained language models. Each program composes alpha-masked layers whose shared spatial expressions define coverage and physically based rendering (PBR) channels, making dependencies between patterns, color, and relief explicit. A standalone interpreter evaluates the program into material maps, while the source retains named fields and layer parameters for subsequent authoring. Without task-specific fine-tuning, our pipeline uses parser-guided repair and preview-based critique to revise material designs, then searches noise seeds while keeping each candidate's remaining source fixed. On a curated benchmark of 141 prompts evaluated with six backbones, our best-performing configuration achieves higher mean scores than three diffusion baselines on all four flat-layout prompt-alignment metrics. Its initial programs already exceed all three baselines on mean BLIPScore, before critique or seed search. Retained programs have a median length of 21 lines when pooled across backbones. In a blind four-way comparison involving 30 participants and 20 prompts, our renders receive 59.2% of choices, compared with 19.3% for the most-preferred baseline. Compact executable programs thus offer a way to generate prompt-aligned materials while retaining their construction as part of the asset.

Anson Y. Lam, Shuqing Li, Michael R. Lyu

Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong, China

3D Asset Generation LLM-Based Program Synthesis Physically Based Rendering

Sep 30, 2026cs.SE

Adaptive-GEPA: Make Your Harness Fit Heterogeneous Requests

Reflective optimizers such as GEPA improve language model prompts from execution traces and evaluator feedback; full-program extensions can also rewrite tools and control flow. In practice, a user hands the same endpoint heterogeneous requests whose effective solutions require different tools, reasoning modes, and control flow. Optimizing one shared program leaves this division of work implicit in source-code search, while optimizing a separate program per request family fixes it beforehand. We introduce Adaptive-GEPA, which learns both how to divide requests and how to solve them. It evolves a router and a library of specialist programs under one search budget. The router's instructions, each specialist's description, and its program code are plain, human-readable text, edited from feedback. To combine branches, it aligns specialists by the requests they handle and inherits descriptions together with programs. On a fixed mixture of four task families, the reported Qwen3-8B run evolves four experts without supplying family labels to the router or reflection model; its routing matches the task partition on all 651 test requests. Its family-mean test score (x100) rises from 52.6 to 70.6, compared with 62.5 for GEPA's full-program adapter and 54.0 for GRPO at a nominal budget of 18,000 scored calls. These counts do not equate total compute. Figure 1 summarizes the learning curves, final test scores, and routing agreement.

Tianyu Chen, Yasi Zhang, Ruiyi Wang +3

University of Texas at Austin · University of California, Los Angeles · University of California, San Diego +3

Large Language Model-Guided Optimization LLM-Based Program Synthesis Agent Harness Optimization LLM Routing

Sep 30, 2026cs.AI

Code to Control: Synthesizing Parameterized Reactive Controllers

Recent LLM-based approaches to control either invoke a language model to select actions or synthesize world models that require planning at every decision, introducing latency that can limit real-time use. We introduce Code to Control, an approach that synthesizes Python controllers which execute directly as policies. Code to Control separates program structure from parameters. An LLM synthesizes the controller structure, while derivative-free search fits its parameters for continuous control using feedback from the environment. Once learned, the resulting controllers require neither LLM inference nor planning at decision time, enabling real-time gameplay and, under our timing protocol, faster action selection than a PPO policy. Across a suite of Atari games, Flappy Bird, and MuJoCo tasks, Code to Control outperforms planning-based program synthesis methods, remains competitive with deep reinforcement learning while using fewer environment interactions, transfers across substantial changes in environment dynamics, and scales to complex locomotion tasks.

Zergham Ahmed, Joshua B. Tenenbaum, Chris Bates +1

Harvard University · Massachusetts Institute of Technology · Florida Institute for Human and Machine Cognition

RL Control Language Model-Based Control LLM-Based Program Synthesis Derivative-Free Optimization

Sep 29, 2026cs.AI

Component-Aware Feedback for Self-Evolving Programs

LLM-guided evolutionary search can discover complex programs, but existing methods mostly only save candidate programs and fitness scores while discarding which component edits produced which fitness metric changes. Existing methods force the mutator LLM to infer the effect of prior edits from cluttered histories, making program search slow and unstable. This is especially true for locally servable LLMs to evolve multi-component systems. We introduce component-aware feedback, which compares each evaluated program with its parent, identifies the components that changed, and logs them with the associated metric differences into an attribution memory that later mutations read. The memory keeps each change in two reference frames, local against the parent it came from and global against the seed program, which shows both the immediate effect of a change and the cumulative progress made since the seed. We study this on LLM reranking, a multi-objective optimization problem where a multi-stage pipeline must balance quality against serving cost. Across twelve \textsc{Bright} datasets, our method reaches the strongest baseline's final quality after a median of one third of the search budget and ends 7.2% higher in held-out nDCG@10, and under a cost-aware objective it finds pipelines that are on average more accurate while using 11% fewer tokens per query, showing component-aware feedback to be a promising direction for more efficient self-evolving systems.

Ethan Lin, Jinming Nian, Yi Fang

Santa Clara University

Large Language Model-Guided Optimization LLM-Based Program Synthesis LLM Reranking Credit Assignment

Sep 29, 2026cs.LG

Synthesis Without Training: An Inference-Only Pipeline for Tabular, Temporal, and Relational Synthetic Data

Synthetic data generation is dominated by the fit-then-sample paradigm: a generative model is trained on a private dataset and then sampled from. Despite its widespread adoption, this paradigm faces three challenges: (1) a new training run is required for every dataset; (2) different data modalities, such as single tables, time series, and relational databases, require task-specific models and feature engineering; and (3) the resulting model is opaque, making its behavior under data constraints difficult to inspect. We propose GENSCRIPT, an inference-only pipeline that eliminates model training. GENSCRIPT computes a deterministic statistical profile of the source data (column types, ranges, missingness, categories, correlations, etc.) and passes it--rather than raw rows--to a language model to infer field semantics and cross-column integrity constraints. A coding agent then compiles the profile and constraints into an executable, auditable sampler. This unified approach supports single-table, temporal, and relational data without task-specific modeling. Across four single-table benchmarks, GENSCRIPT builds generators in 2 minutes and samples 50k rows within 6 seconds, while remaining within a few points of leading methods in marginal fidelity. Notably, it is the only method that perfectly preserves a 1-to-1 mapping between columns in the Adult dataset. On a smart-building dataset, it produces conditional time series that more closely match the real distribution than two baselines and perfectly preserves primary- and foreign-key relationships in the corresponding relational database.

Zilong Zhao, Abdul Raheem, Jiayu Li +5

Betterdata AI · National University of Singapore · University of Illinois Urbana-Champaign +1

Constrained Generative Modeling Synthetic Data Generation Time Series Generation LLM-Based Program Synthesis Synthetic Tabular Data Generation

Sep 29, 2026cs.PL

DatalogBench: Evaluating Large Language Models on Text-to-Datalog Synthesis

Datalog underpins reasoning tasks such as program analysis, but its programs are hard to write. Existing synthesizers automate this task but require users to state their intent as input-output examples. Large language models (LLMs) suggest a more natural route, text-to-Datalog synthesis from a natural-language question, yet how well they do so has not been systematically evaluated. We present DatalogBench, a benchmark of 136 text-to-Datalog synthesis tasks curated from existing Datalog-based artifacts. Synthesized programs are graded by execution on held-out inputs against an oracle validated by mutation analysis. Across six LLMs and four prompting configurations, exact match peaks at 68.4%, and relation descriptions or an input-output example have only modest, model-dependent effects. Under direct prompting, most failures occur at compile time, typically because a model invents auxiliary predicates that it never declares or types consistently. Two coding agents reach up to 83.8% and eliminate nearly all such failures, leaving mostly semantic errors concentrated in recursive tasks. DatalogBench thus identifies recursive reasoning and decomposition as open challenges for current LLMs and agents, and offers a reliable, execution-grounded measure of both.

Yuan Li, Hanyun Jiang, Guowei Tian +2

The State Key Laboratory of Blockchain and Data Security, Zhejiang University · National University of Singapore

LLM Evaluation LLM-Based Program Synthesis Implicit Reasoning in Language Models

Sep 28, 2026cs.LG

From Experience to Expertise: Adoption-Aware Memory Learning for Data-Scarce NPU Kernel Synthesis

High-performance kernels underpin efficient accelerator execution but require expert tuning and lengthy manual optimization cycles. LLM coding agents promise automation, yet their CUDA knowledge transfers poorly to data-scarce domain-specific architectures (DSAs) such as NPUs, whose execution models and memory hierarchies differ substantially from those of GPUs. To address this transfer gap, post-training methods adapt LLMs to NPU programming but depend on scarce expert data and substantial training compute. Memory-learning agents instead adapt through external memory, but their uniform credit assignment gives adopted and unused experiences the same reward target, potentially biasing subsequent retrieval rankings. Moreover, when learned values guide only retrieval, high-value experiences that generalize across operators must be retrieved repeatedly rather than retained in context, thereby increasing retrieval overhead and weakening cross-task guidance. We therefore present SAGE, a persistent self-improving agent for NPU kernel synthesis. Adoption-Traced Utility estimation (ATU) combines explicit adoption records with kernel evaluation outcomes for adoption-aware credit assignment. Utility-Gated Consolidation (UGC) uses positive utility and repeated adoption across operators to select and abstract reusable rules into a bounded resident context. On NPUKernelBench, SAGE achieves a 95.5% execution rate versus 84.1% for the strongest controlled baseline, with 86.9% of solved operators outperforming torch_npu. With GLM-5.3, SAGE achieves a 43.99x speedup over the torch_npu reference on sparse flash attention. These results show that adoption-aware credit assignment and selective consolidation enable agents to accumulate and reuse hardware-specific knowledge across tasks.

Longxiao Fan, Tao Zhang, Han Yan +5

Fudan University · University of Science and Technology of China · Huawei Technologies Ltd.

LLM-Based Program Synthesis Agent Skill Learning Memory-Augmented Agents

Sep 28, 2026cs.PL

Semantic Prefix Oracles for LLM Decoding: Contracts and Differential Validation

Constrained decoding can enforce regular or context-free output formats, but many program-generation failures are semantic: scope, typing, and declaration effects depend on context. We present semantic grammar specifications, a declarative formalism that attaches such constraints to a context-free surface and executes them during Earley descent. Our implementation enforces \emph{safe pruning}: it rejects only prefixes whose semantic contradictions cannot be repaired by any continuation. A separate, grammar-dependent, \emph{dead-end freedom} property guarantees the existence of a realizable witness for each remaining branch. We give simple sufficient conditions based on surface productivity, type coverage, and left-to-right constraint flow. Our finite-lambda, core ML, and C-like fragments satisfy them, while the STLC instance used in our experiments does not: plain STLC can violate type coverage, and we show how restricting its type universe recovers it. A tokenizer-lifting lemma carries character-level witnesses to token sequences under an explicit vocabulary-coverage hypothesis. We validate the implementation differentially against production compilers (\texttt{ocamlc}, \texttt{cc}). Across every prefix of 65 compiler-valid programs we observe zero false prunes. The semantic oracle localizes 25/30 invalid programs mid-stream, against 0/30 for a syntax-only oracle, and agrees on 42/42 recursion probes. A twelve-model generation study, including a matched semantic-versus-syntactic ablation for nine models, finds nonnegative observed semantic-minus-syntactic point estimates for every model-language pair, with maxima of

+15.2

points on STLC task correctness and

+14.3

points on ML validity.

Paul Kronlund-Drouault

ENS de Lyon Lyon, France · Unsuspicious Industries Paris, France · Université de Lille Lille, France

Constrained Decoding LLM-Based Program Synthesis Program Synthesis Grammar-Constrained Decoding

Sep 28, 2026cs.CL

ReMCTS: Reflection-Enhanced Monte Carlo Tree Search for Code Generation

Open-weight large language models (LLMs) can generate function-level programs from natural-language prompts, but plausible candidates still fail on hidden semantics and repeat mistakes across repair attempts. We present ReMCTS, an execution-grounded, memory-augmented, LLM-guided MCTS-style search framework. It organizes program candidates as tree states, retains branch-local debugging context, retrieves failure experience across branches, and distinguishes failed checks from unavailable evidence. On HumanEval and MBPP-Sanitized, visible-test ReMCTS improves over direct generation in 8 of 10 model-dataset pairs under held-out evaluation, whereas proxy-only search is less stable. Controlled tree-search, sampling, repair, and memory ablations characterize the source and limits of these gains. A 30-task HumanEval-X C++ pilot further demonstrates compatibility with compiler-backed execution, but does not constitute a broad multilingual evaluation.

Huifei Wang, Xinying Huang, Yiheng Sun +1

College of Computer Science and Software Engineering, Shenzhen University · School of Artificial Intelligence, Shenzhen University

Execution-Guided Code Generation LLM-Based Program Synthesis Monte Carlo Tree Search LLM Code Generation Memory-Augmented Language Model Agents

Sep 28, 2026cs.AI

LLMs for Executable Multi-Agent System Specification Generation

MAS specifications express the effects of the actions of the agents and their environment, as well as other temporal phenomena, such as the intervals during which an agent may perform an action. The specification of a MAS should also be executable in order to allow for run-time monitoring. Constructing the specification of a MAS requires formal language expertise, while machine learning techniques depend on labelled data which are rarely available. To address these issues, we propose

genRTEC', a method that leverages pre-trained Large Language Models (LLMs) to generate executable MAS specifications, in the language of the

Run-Time Event Calculus' (RTEC), from natural language descriptions. genRTEC constructs MAS specifications with complex hierarchical and cyclic dependencies based only on short natural language descriptions of the concepts involved. We present an extensive empirical evaluation of genRTEC, spanning various MAS specifications, including both a qualitative and a quantitative assessment. Our results demonstrate that genRTEC constructs executable MAS specifications of high predictive accuracy without compromising reasoning efficiency.

Andreas Kouvaras, Periklis Mantenoglou, Alexander Artikis

University of Piraeus, Greece. · Örebro University, Sweden. · NCSR “Demokritos”, Greece.

LLM-Based Program Synthesis Multi-Agent Systems

Sep 27, 2026cs.SE

RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluation

Translating natural-language access-control requirements into policies requires careful reasoning about permissions, constraints, and exceptions, and even frontier LLMs often produce policies that violate the intended authorization semantics. We construct CedarInstruct, to our knowledge the first dataset that supports both training and semantic evaluation for formally verifiable Cedar policy synthesis. It contains 5,800 scenarios across 44 domains and 1,408 representing a single synthetic organization, each with a verified target policy and an executable verification plan. On this data we introduce RAISE, which trains policy synthesizers from formal verification in two stages, verified supervised fine-tuning (SFT) followed by a reinforcement learning (RL) stage that learns from verifier signal. We find that SFT succeeds largely by letting models express authorization logic they already have, since untrained models rarely write valid Cedar but often reason correctly when they do. After SFT, how the verifier's information is used matters more than how much of it is used. Of six RL instantiations that consume progressively richer verifier signal, only RAISE-OC improves meaningfully on SFT; it turns failed checks and symbolic counterexamples into guided exploration and learns from the result with off-context GRPO. With about 5.4K verified scenarios and LoRA fine-tuning, RAISE-OC trains Qwen3.5-9B to surpass zero-shot GPT-6 Astra and Claude Opus 5 by 13.33 and 16.26 percentage points in semantic success on held-out scenarios, and training transfers to the independently constructed CedarBench.

Yingming Zhou, Adarsh Vatsa, William Eiers

Stevens Institute of Technology

RL for Language Model Reasoning LLM-Based Program Synthesis Access Control

Sep 24, 2026cs.RO

Coding Agents for Generalized Task and Motion Planning Problems

Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometric, kinematic, and dynamic constraints. Generalized TAMP addresses this difficulty by exploiting regularities across problem instances to reduce planning effort on new instances. However, existing methods require substantial TAMP-specific engineering. We investigate whether coding agents can automate this process by synthesizing programs that generalize across instances. Given a task description and simulator access, each agent chooses how to interact with the environment while developing a program within a fixed synthesis budget. The program is then frozen and evaluated on unseen instances. We evaluate Claude Code (Opus 5) and Codex (GPT-5.6 Sol and GPT-6 Astra) on 28 simulated environments from KinDER and PDDLStream, with object counts beyond those evaluated in the original benchmark. Across all program synthesis methods, we evaluate 980 generated programs on 100 held-out instances each, 98,000 evaluation episodes in total. Overall, we find that coding agents are surprisingly effective at generalized TAMP: all three agent configurations outperform hand-engineered planners, one-shot generation, and an LLM-based generalized planning baseline in mean success (56% to 95% versus 47% for the planners, on the 16 environments where a planner is available). As object counts grow, the agents' programs maintain higher success than the planner, using an order of magnitude less computation per instance on average. Logs show agents using interaction to calibrate physical models, test edge cases, and refine strategies. We release all code, including the full prompts given to the agents. These findings suggest that coding agents are a strong baseline for generalized TAMP.

Matteo Merler, Bowen Li, Josh Roy +4

Fondazione Bruno Kessler · Carnegie Mellon University · Princeton University +1

Coding Agents LLM-Based Program Synthesis Robot Task Planning

Sep 23, 2026eess.SY

Evolving Inspectable O-RAN Slicing xApps with LLMs

Open RAN (O-RAN) slicing xApps must adapt resource allocations to changing channel conditions and traffic demands while meeting service-level agreements (SLAs). Deep reinforcement learning can produce adaptive policies, but their allocation rules remain encoded in neural-network parameters. Our goal is to retain this adaptability while making the controller's decision logic directly inspectable and editable by operators. We use a large language model (LLM) to evolve slicing controllers as compact Python programs whose decision logic remains readable and editable after optimization. The LLM proposes and revises candidates offline, while a calibrated simulator scores them, and the selected decision module runs unchanged in the O-RAN control path. On the NSF POWDER 5G testbed, the evolved controller releases resources from a guaranteed slice whose throughput target becomes unattainable under a sustained channel fade, improving best-effort throughput from 158.2 to 228.6 Mbps, a 44.5% gain over the best static allocation. Since the controllers are readable source code, their behavior can be predicted from their equations, defects can be diagnosed by reading the code, and calibration errors can be corrected with one-line edits, reducing SLA misses from 79.9% to 2.2% in one case and more than doubling fitness in another. In a four-slice trace-driven simulation calibrated to the same testbed, evolutionary search achieves higher average evaluation scores than independent prompting at a matched proposal budget, with mean normalized gains on held-out traces of 16.3% for prompting alone, 32.1% for evolution from scratch, and 51.0% for evolution from a starting program.

Faezeh Dehghan Tarzjani, Bhaskar Krishnamachari

Department of Electrical and Computer Engineering, University of Southern California

Large Language Model-Guided Optimization LLM-Based Program Synthesis Open Radio Access Network Wireless Resource Allocation

Sep 23, 2026cs.NE

Combining LLMs and Genetic Search for ARC-AGI-2

LLMs can generate programs for ARC-AGI-2 tasks, but the provided compute only allows a small number of attempts to generate, debug and validate solutions. Genetic algorithms can search and test many more programs, but random search rarely starts in a useful neighborhood of the solution space. We combine the two methods through a compact domain specific language (DSL). First, a quantized Qwen3.5-4B LLM generates an initial set of programs for each ARCAGI-2 task. Then, we use those programs to seed an initial population of starting programs, and use genetic algorithms to evolve these programs towards a solution to the given task. The DSL is designed such that every mutated program remains valid and can be executed. The initial programs proposed by the LLM solve 2 (3.3%) of the first 60 tasks of the ARC-2 public evaluation set. The genetic algorithm solves an additional 4, giving 6 correct test outputs in total (10.0%). If we try using evolving solutions without this LLM seeding, we do not arrive at any solutions at all. The results show that genetic search can improve programs generated by LLMs and produce additional correct solutions.

Val Dyachenko

Large Language Model-Guided Optimization Genetic Programming LLM-Based Program Synthesis ARC-AGI

Sep 21, 2026cs.NE

Online Automated Algorithm Design with Large Language Models

Large language models (LLMs) enable automated algorithm design (AAD) through reasoning and code synthesis. However, most existing LLM-based AAD methods separate algorithm design from target optimization, deploying a fixed design even as the optimization state evolves. Conventional adaptive optimizers can respond to such changes, but their adjustments remain confined to predefined parameters, operators, or strategies. To address these limitations, we introduce online LLM-based AAD, a novel optimization paradigm that treats the algorithm itself as a state-dependent decision variable. At each stage, LLM agents synthesize an algorithm with new behavior logic from the current optimization state. Executing the generated algorithm advances the search and provides feedback for subsequent designs, coupling algorithm design with target optimization without requiring a separate offline algorithm pretraining stage. To implement this paradigm, we propose OnDesign, a multi-agent framework that reconciles competing design perspectives to synthesize executable algorithms and uses execution feedback to refine how runtime evidence is interpreted for subsequent designs. We evaluate OnDesign across two mainstream black-box optimization paradigms on three scenarios: Bayesian optimization, evolutionary continuous optimization, and evolutionary mixed-variable optimization. Extensive experiments on six benchmark suites and one engineering problem across multiple problem dimensions demonstrate superior overall performance over conventional optimizers and offline LLM-based AAD methods.

Zhiyao Zhang, Yichen Li, Xingyu Wu +2

Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University, Hong Kong SAR 999077, China · College of Computer Science, Chongqing University, Chongqing 400044, China

Automated Algorithm Discovery Black-Box Optimization LLM-Based Program Synthesis

Sep 20, 2026cs.CR

SyzHarness: Patch-Based Kernel Bug Reproduction with LLM-Synthesized Fuzzing Harnesses

Automated kernel vulnerability reproduction is essential for bug triage, patch validation, and regression testing, but still lacks an effective and efficient solution. The core challenge is twofold: a reproducer must first recover the trigger scaffold needed to reach the vulnerable state and determine the precise concrete values that actually trigger the bug. Existing directed fuzzing approaches are ineffective at recovering the necessary trigger scaffold, while LLM-only generation is brittle because it struggles with concrete-value discovery and runtime nondeterminism. We design SyzHarness, a framework that combines LLM reasoning with coverage-guided fuzzing for patch-based Linux kernel vulnerability reproduction. Given a patch, SyzHarness uses an LLM agent grounded by code navigation tools to synthesize a parameterized fuzzing harness that fixes the prerequisite setup logic while exposing only uncertain, bug-critical input parameters to be mutated by Syzkaller. SyzHarness then translates this harness into a Syzkaller compatible interface and iteratively refines it using hierarchical reachability feedback. We evaluate SyzHarness on multiple datasets of triggerable real-world Linux kernel vulnerabilities. On 100 KernelCTF cases, SyzHarness achieves a 78% bug reproduction success rate. On the SyzDirect benchmark, SyzHarness achieves a 73% bug reproduction success rate, substantially outperforming prior directed greybox fuzzing. On 50 recent, known-triggerable syzbot bugs fixed after March 2026, SyzHarness reproduces 40/50 (80%) using only the fix commits as input.

Xingyu Li, Juefei Pu, Haonan Li +4

University of California, Riverside

Software Vulnerability Detection LLM-Based Program Synthesis Software Security Automated Test Generation

Sep 14, 2026cs.AI

AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery

Large language models have advanced automated algorithm discovery by synthesizing executable code, but existing frameworks trap them in rigid search pipelines with pre-defined control flows. This limitation restricts adaptive reasoning, blocks cross-paradigm transfer, and overlooks richer execution feedback. To bridge this gap, we introduce an end-to-end framework, AlgoEvo, a unified agentic architecture that transforms automated algorithm discovery into an interactive, knowledge-accumulating process. An autonomous agent dynamically inspects, diagnoses, and edits code based on runtime feedback. A design skill hub decouples paradigm-specific knowledge from the core discovery engine, allowing a unified workflow to seamlessly handle single-heuristic, multi-objective, and multi-component design. Meanwhile, a hierarchical experience bank organizes search trajectories into a task-level tree to guide exploration and consolidates cross-task patterns into reusable skills. Across six representative benchmark tasks, AlgoEvo reaches state-of-the-art performance with as little as 7% of the evaluation budget and reduced token consumption, demonstrating strong intra-task accumulation, cross-task transfer, and the ability to reproduce or exceed the strongest existing methods through flexible skill activation.

Junhao Qiu, Qinglong Hu, Ji Cheng +3

Department of Computer Science, City University of Hong Kong · Huawei Noah’s Ark Lab · Institute of Advanced Intelligence and Computing, A*STAR

Automated Algorithm Discovery Automated Heuristic Design LLM-Based Program Synthesis Agent Skill Learning Self-Evolving Agents

Sep 14, 2026cs.CL

Local Edits, Global Ripples: Replay-Informed Policy Adaptation for Workflow Synthesis

Prompt-policy editing offers a practical way to improve agents that synthesize executable workflows without updating the underlying model. However, persistent prompt editing has two coupled properties. First, edit locality does not imply effect locality: an edit confined to one policy segment can ripple through downstream execution, altering behavior beyond the edited segment. Second, edit effects are composition-sensitive: edits that work in isolation can interfere after composition, causing one or both to lose their benefit or become harmful. Persistent adaptation must therefore support two distinct decisions: identifying where the policy should change from execution feedback, and determining whether the resulting edit remains safe to persist after composition. To address these challenges, we introduce RIPPLE (Replay-Informed Persistent Policy Localization and Editing), which separates where an edit is made from whether it remains safe after composition. It diagnoses failed trajectories, maps each actionable failure to a predefined policy segment, and restricts the correction to that part of the policy. RIPPLE then evaluates candidates against the same iteration-start policy to compare their isolated gains, before replaying promising edits after previously accepted updates to expose downstream effects and interactions. Only edits that remain safe under composition are retained. We evaluate RIPPLE on Flow-HO, a synthetic held-out benchmark for executable workflow synthesis. RIPPLE improves validation success by up to 23.1% and yields positive gains on two additional frozen language-model backbones, while maintaining edit efficiency and low execution cost. Targeted interaction analysis further demonstrates both properties: a segment-local tool-use edit changes downstream resource resolution and validation, while an edit beneficial in isolation becomes harmful after composition.

Manqing Mao, Hong Wang, Samson Koelle +8

Amazon, Inc.

Agentic Workflows LLM-Based Program Synthesis

Sep 14, 2026cs.NI

NDT Factory: Synthesizing Verified Network Digital Twins from Semantic Models via Multi-Agent LLM

Autonomous network management requires systems that can evaluate Network Service Intents (NSIs) under varying conditions without manual implementation of analysis logic, as envisioned in TM Forum Level~4 (L4) autonomy. Behavioral Network Digital Twins (NDTs) enable such evaluation, but existing NDTs rely on pre-defined analytical logic, limiting adaptability for evolving closed-loop control. This paper introduces the NDT factory, a multi-agent software system that synthesizes executable behavioral NDTs on demand from semantic models using Large Language Model (LLM). We validate the system using a Call Admission Control (CAC) case study, where deterministic what-if analysis serves as the admission decision process. The NDT factory generates a complete CAC NDT through parallel synthesis and orchestration, achieving 100% compilation and test pass rates across multiple runs. Simulation over 300 NSIs shows 99.3% decision agreement with a reference implementation, 90% admission rate, and correct attribution of all rejections, demonstrating reliable synthesis with deterministic, verifiable execution.

Sudipta Acharya, Petar Djukic, Burak Kantarci

University of Ottawa, Ottawa, ON, Canada · Bell Labs Research, 600 March Road, Kanata, ON K2K 2E6, Canada

Multi-Agent LLM Systems LLM-Based Program Synthesis Digital Twins

Sep 3, 2026cs.CL

Compile by Training: Turning Natural-Language Specifications into Local Neural Functions

Many recurring text functions are easy to describe but difficult to implement with rules, while calling a large remote model for every input introduces repeated cost, latency, and dependency on a provider. We present compile by training, which turns a natural-language specification into a reusable neural function. At compile time, teacher models generate task-specific examples that are used to train a small adapter for a compact interpreter. The resulting function runs without the teachers and can be stored, versioned, and composed like ordinary software. On FuzzyBench-Hard, a subset on which the Program-as-Weights fast compiler produced no exact matches, compile by training reaches 83.6% semantic accuracy. This higher accuracy comes with a higher compile-time cost: roughly a minute rather than seconds for the fast compiler. We deploy the compiler in a public interactive service and demonstrate compiled functions in a multi-site website helper, a language-controlled 3D avatar, and a bidirectional English-Claudish translator.

Yuntian Deng, Pengyu Nie, Stuart Shieber

University of Waterloo · Harvard University

LLM-Based Program Synthesis

Aug 31, 2026cs.RO

SUN: Persistent Programs For Language-Grounded Control-to-Learning-to-Real Policies

Bridging model-based control and learned policies in long-horizon manipulation has harbored a silent disagreement: control executes specified objectives, learning amortizes that behavior into a reactive policy, yet existing protocols discard task semantics, leaving rewards hand-crafted and behavior drifting from what control verified.We introduce Semantically UNified (SUN) Programs, typed executables where geometric and contact relations are defined once and compiled into aligned Model Predictive Control (MPC) costs, satisfaction predicates, RL rewards, transition guards, and diagnostics. Our system, Kuafu, driven by large vision language systems, automatically synthesizes SUN Programs from language and scene semantics, screens feasibility via MPC, and retains semantics while training stage-conditioned policies. Across nine tasks, Kuafu achieves 82.03% macro-success, outperforming sparse-reward (35.67%) and Stage-BC (24.75%) baselines. At 8192-way scale, it generates 10.57x the successful trajectory time per hour of human teleoperation. With 500 trajectories per task, Kuafu data trains DP3 policies to 46.0% simulation success (vs. 22.4% for alternatives) and 34.7% on physical Franka and Kinova robots. These results establish that simulation-screened task semantics can effectively amortize control into robust policies, without demonstrations or manual dense rewards, unifying symbolic planning and data-driven execution.

Weiqi Wang, Zhi Li, Yudong Lei +7

University of California, Los Angeles · University of California, Santa Barbara · Amazon +1

Robot Policy Learning Long-Horizon Robotic Manipulation Language-Conditioned Robot Manipulation LLM-Based Program Synthesis Robotic RL

Aug 31, 2026cs.AR

LLM-based Hardware Development with Hierarchical IRs and End-to-End Multi-Agent Workflow

Large language models (LLMs) are increasingly used in software development, but their use in complex hardware design remains limited. This gap stems from both the scarcity of public hardware training data and the fundamentally different methodologies used in hardware design. In particular, applying LLMs to hardware requires more than direct RTL generation: the model must understand module boundaries, inter-module connections, and verification requirements. In this paper, we present an LLM-based hardware development framework with hierarchical intermediate representations (IRs) and an end-to-end multi-agent workflow. The core idea is to provide an abstraction of hardware design to LLMs through two structured IRs: Architectural Sketch, which captures module topology and interconnection, and Operational Specification, which defines per-module functionality and interfaces. Our framework uses these IRs to decompose a complex design into sub-modules, specify the per-block functionality, and derive how each module should be tested and verified. We incorporate a multi-agent debug loop in the framework, allowing agents to get the error feedback and control the debug details such as the signals to be probed for simulation. We evaluate our framework on Verilog-Eval benchmark, achieving a pass@5 rate of 95.5%, which surpasses current state-of-the-art LLM generation frameworks. To better assess performance on complex, realistic designs, we introduce a new case study spanning applications from general-purpose processors to digital signal processing systems. Experimental results indicate that such complex designs exceed the capabilities of existing approaches, whereas our framework is the only one capable of producing functional end-to-end design. Our generated RTL follows all industry-standard design rules, is lint-clean, functionally correct and fully synthesizable.

Chenyang Yin, Agasthi Haputhanthri, Aditya Anirudh Jonnalagadda +7

National University of Singapore · Shandong University · Stanford University +1

Electronic Design Automation LLM-Based Program Synthesis LLM Code Generation

Aug 31, 2026cs.AI

Generating Workflow DAGs from Natural Language with Non-Reasoning LLMs

This paper addresses the problem of translating natural-language routing rules written by business administrators into executable workflow graphs for enterprise contact centers. Each target is a directed acyclic graph (DAG) of conditional actions with parallel branches, hit-first fallback chains, and per-branch Boolean predicates, encoded in the JSON dialect of a commercial routing platform. We show that neuro-symbolic decomposition enables lower-cost, non-reasoning large language models to generate complex workflow DAGs at production-relevant quality without expensive extended-reasoning models. Our central diagnostic is an emission-density bottleneck: on a 635-rule benchmark of manufactured synthetic data, models select the correct graph nodes with high accuracy but increasingly misconfigure attributes and Boolean grouping as the number of interdependent nodes emitted in one pass grows. We therefore move combinatorial graph construction from the model into a deterministic compiler driven by a compact intermediate representation, with a learned registry-selection front end that focuses generation on relevant vocabulary. Across four models, the full system reaches approximately 89% LLM-judge validity, approximately 90% exact-match condition accuracy, and 99-100% valid JSON while using roughly half the per-rule prompt tokens of a monolithic prompt. On GPT-5.3-chat, the method improves judge validity by 24 percentage points and achieves statistical equivalence to a reasoning model's out-of-the-box quality, although an approximately 8-point frontier gap remains. We also present a deployment path and transferable lessons for structured-generation applications.

Anand Iyer, Bhanu Khetharpal, Srinivas Upadhya +1

Microsoft

LLM-Based Program Synthesis Structured Output Generation Neuro-Symbolic AI