Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.
super hub Mixed citations
Program Synthesis with Large Language Models
Mixed citation behavior. Most common role is background (52%).
532
Pith papers citing it
Background
52% of classified citations
abstract
This paper explores the limits of the current generation of large language models for program synthesis in general purpose programming languages. We evaluate a collection of such models (with between 244M and 137B parameters) on two new benchmarks, MBPP and MathQA-Python, in both the few-shot and fine-tuning regimes. Our benchmarks are designed to measure the ability of these models to synthesize short Python programs from natural language descriptions. The Mostly Basic Programming Problems (MBPP) dataset contains 974 programming tasks, designed to be solvable by entry-level programmers. The MathQA-Python dataset, a Python version of the MathQA benchmark, contains 23914 problems that evaluate the ability of the models to synthesize code from more complex text. On both datasets, we find that synthesis performance scales log-linearly with model size. Our largest models, even without finetuning on a code dataset, can synthesize solutions to 59.6 percent of the problems from MBPP using few-shot learning with a well-designed prompt. Fine-tuning on a held-out portion of the dataset improves performance by about 10 percentage points across most model sizes. On the MathQA-Python dataset, the largest fine-tuned model achieves 83.8 percent accuracy. Going further, we study the model's ability to engage in dialog about code, incorporating human feedback to improve its solutions. We find that natural language feedback from a human halves the error rate compared to the model's initial prediction. Additionally, we conduct an error analysis to shed light on where these models fall short and what types of programs are most difficult to generate. Finally, we explore the semantic grounding of these models by fine-tuning them to predict the results of program execution. We find that even our best models are generally unable to predict the output of a program given a specific input.
hub tools
citation-role summary
background 58
dataset 41
method 4
other 2
citation-polarity summary
claims ledger
- abstract This paper explores the limits of the current generation of large language models for program synthesis in general purpose programming languages. We evaluate a collection of such models (with between 244M and 137B parameters) on two new benchmarks, MBPP and MathQA-Python, in both the few-shot and fine-tuning regimes. Our benchmarks are designed to measure the ability of these models to synthesize short Python programs from natural language descriptions. The Mostly Basic Programming Problems (MBPP) dataset contains 974 programming tasks, designed to be solvable by entry-level programmers. The M
authors
co-cited works
representative citing papers
A new benchmark with cognitive traps shows frontier deep research agents achieve only 13-16% acceptance on expert consulting tasks under combined verifier and rubric criteria.
BoLT is a benchmark of surrogate models fitted to real LLM experiment data that enables evaluation of Bayesian and black-box optimization methods on multi-fidelity, multi-objective, high-dimensional LLM tasks.
PDEAgent-Bench is the first multi-metric, multi-library benchmark for AI-generated PDE solvers, evaluating executability, numerical accuracy, and efficiency across DOLFINx, Firedrake, and deal.II.
SimWorld Studio deploys an evolving coding agent to create adaptive 3D environments that co-evolve with embodied learners, delivering 18-point success-rate gains over fixed environments in navigation benchmarks.
Backdoored model code enables deterministic, verifiable stealing of sparse secrets during local LLM fine-tuning via tensor-rule matching and gradient injection, achieving over 98% strict attack success rate while bypassing DP-SGD and auditing defenses.
StabilizerBench is a new benchmark for evaluating AI agents on generating, optimizing, and making fault-tolerant stabilizer circuits for quantum error correction, with efficient verification and multi-tier scoring.
NLI autonomously discovers a vocabulary of primitive operations and interprets variable-length programs via a neural executor, allowing end-to-end training and gradient-based test-time adaptation that outperforms prior methods on combinatorial generalization tasks.
Derives an exact unbiased policy gradient for RL post-training of diffusion LLMs via entropy-guided step selection and one-step denoising rewards, achieving state-of-the-art results on coding and logical reasoning benchmarks.
Molmo2 delivers state-of-the-art open-weight video VLMs with new grounding datasets and training methods that outperform prior open models and match or exceed some proprietary ones on pointing and tracking tasks.
CritPt benchmark shows state-of-the-art LLMs reach only 5.7% average accuracy on full-scale unpublished physics research tasks, rising to about 10% with coding tools.
ExCyTIn-Bench is the first benchmark of 7542 questions from Microsoft Sentinel threat investigation graphs, where the best LLM agent achieves a reward of 0.606.
LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
Language models generate robot policy code from natural language commands via few-shot prompting, enabling spatial-geometric reasoning, generalization, and precise control on real robots.
Training language models to generate intermediate computation steps on a scratchpad enables them to perform multi-step tasks such as long addition and arbitrary program execution that they otherwise fail at.
Regression accumulation affects 40-73% of 8-turn LLM coding tasks on extended HumanEval+/MBPP+ benchmarks, with verification gates improving final-turn pass rates on prior tests.
Multi-agent LLMs generate and verify 14,073 deterministic reaction rules from 665,901 patents, enabling 97.7% classification of unseen reactions with finer resolution than fixed proprietary systems.
FRAME adds a learnable fractional-Fourier order per expert in a MoE-LoRA setup so that low-rank updates are placed in the domain where they are most compact, yielding gains over fixed-domain baselines on LLaMA-3.1-8B and Qwen2.5-7B.
Multi-tier verification on VULBENCH-CPP shows AI-generated C++ code triggers confirmed runtime violations roughly twice as often as human code, while static analysis misleadingly indicates parity due to code length.
AxDafny achieves 92.7% verification success on DafnyBench (6.5 points above prior proof-hint baselines) via verifier-guided repair and introduces the LCB-Pro-Dafny benchmark of 250 problems.
Preregistered placebo-controlled decomposition shows external executable counterexamples drive self-repair gains in small code models more than re-exposure or self-critique.
AlgoBench creates traceable variants of competitive programming problems via constraint shifts that invalidate original algorithms, paired with complexity metrics that reveal LLMs often produce functionally correct but asymptotically unsuitable solutions.
Empirical evaluation of three LLMs finds prevalent overconfidence in insecure code generation, with security calibration outperforming functional calibration but both degrading in repository-level settings.
Masked diffusion LMs can use continuous x-prediction flow with token-wise asynchronous updates and an RL policy network to reach 97% performance on HumanEval using only 25% of the usual decoding budget.
citing papers explorer
-
LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection
LEAP detects early-converging tokens in dLLMs via future context filtering and multi-sequence superposition, reducing average denoising steps by about 30% while maintaining accuracy.
-
Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms
Queryable LoRA adds dynamic routing over shared low-rank atoms with attention and language-instruction regularization to make parameter-efficient fine-tuning more adaptive across inputs and layers.
-
CoCoDA: Co-evolving Compositional DAG for Tool-Augmented Agents
CoCoDA co-evolves a typed compositional DAG of primitive and composite tools with the agent planner, using signature-based retrieval and a size-based reward to scale libraries efficiently and let an 8B model match or beat a 32B model on math and code benchmarks.
-
Fast Byte Latent Transformer
BLT-D, BLT-S, and BLT-DV use block-wise diffusion training and speculative verification to enable parallel byte generation in byte-level LMs, cutting memory-bandwidth cost by over 50%.
-
GameGen-Verifier: Parallel Keypoint-Based Verification for LLM-Generated Games via Runtime State Injection
GameGen-Verifier decomposes game specifications into keypoints, injects runtime states for targeted checks, and achieves 92.2% accuracy on 100 games while running up to 16.6x faster than agent-based baselines.
-
An Empirical Study of Proactive Coding Assistants in Real-World Software Development
Real developer IDE traces differ substantially from LLM simulations in behavior and structure; current proactive assistants are unreliable on real traces, and simulated data cannot substitute for real data in training.
-
SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies
SWE-WebDevBench finds that AI app builders commonly fail at translating business needs into complete, secure, production-ready software due to specification bottlenecks, frontend-backend decoupling, low engineering quality, and security weaknesses.
-
Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards
TraceLift trains reasoning planners with executor-grounded rewards that multiply a rubric-based reasoning quality score by measured performance uplift on a frozen executor, outperforming outcome-only training on math and code benchmarks.
-
Deep Graph-Language Fusion for Structure-Aware Code Generation
CGFuse enables deep token-level fusion of graph-derived structural features into language models, yielding 10-16% BLEU and 6-11% CodeBLEU gains on code generation tasks.
-
LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation
LiveFMBench shows that direct LLM prompting for C program formal specs overestimates accuracy by ~20% due to unfaithful behaviors like deceiving provers, while agentic workflows help under low sampling but overall performance remains far below human-authored specs.
-
Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrast
FoCore uses self-contrast on early-converging high-density tokens to boost diffusion LLM quality on reasoning benchmarks while cutting decoding steps by over 2x.
-
MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate
MAD-OPD recasts on-policy distillation teachers as a debating collective to supply better supervision, lifting agentic and code performance over single-teacher OPD across multiple model sizes.
-
Social Bias in LLM-Generated Code: Benchmark and Mitigation
LLMs show up to 60.58% social bias in generated code; a new Fairness Monitor Agent cuts bias by 65.1% and raises functional correctness from 75.80% to 83.97%.
-
Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression
Auto-FlexSwitch achieves efficient dynamic model merging by decomposing task vectors into sparse masks, signs, and scalars, then making the compression learnable via gating and adaptive bit selection with KNN-based retrieval.
-
Intent2Tx: Benchmarking LLMs for Translating Natural Language Intents into Ethereum Transactions
Intent2Tx shows that LLMs often generate syntactically valid but functionally incorrect Ethereum transactions, especially on multi-step and out-of-distribution intents, despite gains from scaling and retrieval augmentation.
-
BoostLoRA: Growing Effective Rank by Boosting Adapters
BoostLoRA grows effective adapter rank linearly via iterative boosting on hard examples with orthogonal low-rank updates, outperforming both single-shot ultra-low-rank adapters and full fine-tuning on math and code tasks with zero added inference overhead.
-
ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation
ClassEval-Pro benchmark shows frontier LLMs achieve at most 45.6% Pass@1 on class-level code tasks, with logic errors (56%) and dependency errors (38%) as dominant failure modes.
-
An Empirical Study of Speculative Decoding on Software Engineering Tasks
Speculative decoding accelerates LLM inference on SE tasks without accuracy loss, with model-based methods suiting code generation and model-free methods suiting repository-level repair and editing.
-
Context-Augmented Code Generation: How Product Context Improves AI Coding Agent Decision Compliance by 49%
Adding product context retrieval to AI coding agents raises decision compliance from 46% to 95% on a new benchmark of 8 tasks with 41 weighted decision points.
-
When Prompt Under-Specification Improves Code Correctness: An Exploratory Study of Prompt Wording and Structure Effects on LLM-Based Code Generation
Structurally rich task descriptions make LLMs robust to prompt under-specification, and under-specification can enhance code correctness by disrupting misleading lexical or structural cues.
-
SWE-QA: A Dataset and Benchmark for Complex Code Understanding
SWE-QA is a new benchmark of 9,072 questions testing multi-hop code comprehension from 12 Python projects, where the best of 15 evaluated models reaches only 74.41% accuracy.
-
Constraint-Guided Multi-Agent Decompilation for Executable Binary Recovery
A constraint-guided multi-agent system turns raw decompiler output into re-executable code at 84-97% success rates, outperforming prior LLM decompilation methods on real binaries.
-
PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement
PhysCodeBench benchmark and SMRF multi-agent framework enable better AI generation of physically accurate 3D simulation code, boosting performance by 31 points over baselines.
-
Assessing the Impact of Requirement Ambiguity on LLM-based Function-Level Code Generation
Orchid benchmark shows requirement ambiguity degrades LLM code generation performance across all models, with advanced models hit hardest, and LLMs rarely detect or resolve the ambiguity themselves.
-
Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RL
Parallel-SFT mixes parallel programs across languages during SFT to produce more transferable RL initializations, yielding better zero-shot generalization to unseen programming languages.
-
Crowded in B-Space: Calibrating Shared Directions for LoRA Merging
Pico reduces LoRA merge interference by calibrating over-shared directions in the B matrix before merging, yielding 3.4-8.3 point accuracy gains and sometimes beating joint training.
-
DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference
DepCap accelerates diffusion LM inference up to 5.63x by using last-block influence for adaptive block boundaries and conflict-free token selection for parallel decoding, with negligible quality loss.
-
Validity-Calibrated Reasoning Distillation
Validity-calibrated reasoning distillation improves transfer of reasoning skills by modulating updates based on relative local validity of next steps instead of enforcing full trajectory imitation.
-
CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation
CodeSpecBench shows LLMs achieve at most 20.2% pass rate on repository-level executable behavioral specification generation, revealing that strong code generation does not imply deep semantic understanding.
-
Structural Anchors and Reasoning Fragility:Understanding CoT Robustness in LLM4Code
CoT prompting in LLM4Code shows mixed robustness that depends on model family, task structure, and perturbations destabilizing structural anchors, leading to trajectory deformations like lengthening, branching, and simplification.
-
AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree Search
AdverMCTS frames code generation as a minimax game where an attacker evolves tests to expose flaws in solver-generated code, yielding more robust outputs than static-test baselines.
-
Many-Tier Instruction Hierarchy in LLM Agents
ManyIH and ManyIH-Bench address instruction conflicts in LLM agents with up to 12 privilege levels across 853 tasks, revealing frontier models achieve only ~40% accuracy.
-
HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?
HiL-Bench shows frontier AI agents fail to ask for help on incomplete tasks, recovering only a fraction of full-information performance, but RL training on Ask-F1 reward improves judgment and transfers across domains.
-
Choose, Don't Label: Multiple-Choice Query Synthesis for Program Disambiguation
Multiple-choice queries synthesized from Hoare triples enable more reliable identification of intended programs than labeled-example supervision in active learning for program disambiguation.
-
DMax: Aggressive Parallel Decoding for dLLMs
DMax uses On-Policy Uniform Training and Soft Parallel Decoding to enable aggressive parallelism in dLLMs, raising TPF on GSM8K from 2.04 to 5.47 and on MBPP from 2.71 to 5.86 while preserving accuracy.
-
Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios
A new benchmark for 0-to-1 CLI tool generation shows state-of-the-art LLMs achieve under 43% success rate with black-box equivalence testing against real oracles.
-
Benchmarking Requirement-to-Architecture Generation with Hybrid Evaluation
R2ABench benchmark shows LLMs generate syntactically valid software architectures from requirements but produce structurally fragmented results due to weak relational reasoning.
-
Evaluating the Environmental Impact of using SLMs and Prompt Engineering for Code Generation
Chain-of-Thought prompting balances high accuracy with low energy use in small language models for code generation, while multi-sampling strategies add high energy costs for small accuracy gains.
-
Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy
LLMs display clear performance stratification on formal language tasks aligned with Chomsky hierarchy complexity levels, limited by severe efficiency barriers rather than absolute capability.
-
Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
DEMASK adds a lightweight pairwise-dependency predictor to dLLMs and uses greedy selection to enable parallel unmasking whose total-variation error is provably bounded under sub-additivity.
-
REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage
REAP automatically curates production-derived benchmarks for AI coding agents via LLM classification and stability checks, producing the Harvest benchmark with model solve rates of 42.9-58.2%.
-
ParetoBandit: Budget-Paced Adaptive Routing for Non-Stationary LLM Serving
ParetoBandit uses contextual bandits with an online primal-dual budget pacer and geometric forgetting to enforce cost ceilings and adapt to non-stationary pricing and quality shifts in LLM serving, achieving 0.4% budget compliance and up to 0.071 quality lift on 1824 prompts.
-
Think Anywhere in Code Generation
Think-Anywhere lets LLMs invoke on-demand reasoning at any token during code generation via cold-start imitation followed by outcome-based RL, reaching state-of-the-art results on LeetCode, LiveCodeBench, HumanEval, and MBPP.
-
Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging
VF-Coder raises GUI code success rate from 21.68% to 28.29% and visual score from 0.4284 to 0.5584 on a new 984-task benchmark by adding direct visual perception and interaction.
-
Synthesis-in-the-Loop Evaluation of LLMs for RTL Generation: Quality, Reliability, and Failure Modes
LLM evaluation for RTL generation identifies three performance tiers with frontier models reaching high synthesis quality and reveals systematic failure differences between proprietary and open models.
-
Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development
Vibe Code Bench evaluates AI models on building complete web applications from specs, with the best of 16 models achieving 61.8% accuracy on the test split using autonomous browser evaluation.
-
Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution
IFCodeEvolve synthesizes coding data via actor-schema co-evolution with MCTS, boosting a 32B model's performance to match proprietary SOTA on instruction following.
-
Improving Sampling for Masked Diffusion Models via Information Gain
Info-Gain Sampler improves MDM decoding by using bidirectional information gain to reduce cumulative uncertainty, outperforming greedy samplers on reasoning accuracy and creative writing tasks.
-
CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training
CapTrack shows post-training causes drift beyond facts, with instruction fine-tuning producing stronger behavioral changes than preference optimization across model families.
-
TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration
TEAM accelerates MoE dLLMs up to 2.2x by exploiting temporal-spatial consistency in expert routing to accept more tokens with fewer activations.