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%).
559
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
Sumi is an openly released 7B parameter uniform diffusion language model pretrained from scratch on 1.5T tokens that matches autoregressive models on several benchmarks.
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.
ELDR reduces median TPOT by 5.9-13.9% in PD-disaggregated MoE serving via expert signatures from prefill, K-means partitioning, and locality-band routing with KV-co-indexed signature cache.
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.
citing papers explorer
-
Draft-OPD: On-Policy Distillation for Speculative Draft Models
Draft-OPD applies on-policy distillation via target-assisted generation and error replay to train speculative draft models, yielding over 5x lossless acceleration and gains over EAGLE-3 and DFlash.
-
Code-QA-Bench: Separating Code Reasoning from Documentation Memorization in Repository-Level QA
Code-QA-Bench uses an answer-first pipeline and three-condition experiments to generate 628 tasks across 10 Python repositories and quantify that code access drives most performance gains while documentation adds only modest benefit on doc-dependent tasks.
-
The Routing Plateau: Understanding and Breaking the Accuracy Limits of LLM Routers
LLM routers across 21 methods on 5 benchmarks converge to similar accuracy below oracle due to learning global performance trends rather than fine-grained query signals.
-
SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling
SuperValid synthesizes capability-aligned OOD validation data to produce a training-free loss metric that correlates with downstream benchmark performance across model architectures, scales, and data distributions.
-
MobileMoE: Scaling On-Device Mixture of Experts
MobileMoE introduces on-device MoE LLMs that match dense models with 2-4x fewer FLOPs and provide efficient smartphone inference.
-
Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching
DecoR routes LLM queries by decomposing them into capability dimensions and matching to historical examples, yielding higher accuracy and lower inference costs than direct-mapping routers on both in-distribution and OOD data.
-
PALoRA: Projection-Adaptive LoRA for Preserving Reasoning in Large Language Models
PALoRA identifies reasoning-critical singular subspaces via SVF and constrains subsequent LoRA updates to be orthogonal to them, preserving 95% of reasoning performance on average across tested models and benchmarks.
-
Design and Report Benchmarks for Knowledge Work
Proposes a three-step benchmark design method (define work activity, specify tested setting, score work product) derived from work studies and O*NET, demonstrated via three case analyses.
-
SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?
SWE-Mutation benchmark shows current LLMs achieve low verification (10.20%) and detection (36.15%) rates on 2,636 mutated variants, exposing weaknesses in generating reliable test suites.
-
Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents
Ratchet provides a minimal hygiene recipe for self-managing skill libraries in frozen LLM agents, delivering +0.328 rolling-mean pass@1 gain on MBPP+ hard-100 and +0.22 peak lift on SWE-bench Verified.
-
Manifold-Guided Attention Steering
MAGS learns low-dimensional subspaces from correct versus incorrect reasoning traces and applies targeted projection corrections to attention heads when they deviate from the correctness manifold during inference.
-
AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows
AgentCo-op retrieves and assembles existing agents and tools into interoperable workflows for open-world scientific tasks, showing effectiveness in genomics case studies and competitive benchmark results with lower costs.
-
DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention
DashAttention introduces differentiable adaptive sparse hierarchical attention via α-entmax block selection, achieving full-attention accuracy at 75% sparsity with improved Pareto performance over NSA and InfLLMv2.
-
AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code
AutoVecCoder combines VecPrompt for automated intrinsic knowledge synthesis and VecRL for efficiency-aligned RL to train an 8B LLM that achieves SOTA on SimdBench SSE/AVX subsets and sometimes exceeds -O3 compiler results.
-
Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning
CodeThinker improves LLM code reasoning via consistency-based RL with stepwise training data, dynamic beam sampling, and consistency rewards, reaching SOTA on benchmarks with 4.3% gains on Qwen2.5-Coder-7B.
-
Contextualized Code Pretraining for Code Generation
Introduces contextualized code pretraining with caller-callee pairs from static analysis to train CallerGen models that outperform baselines on the new CallerEval benchmark.
-
Harnessing LLM Agents with Skill Programs
HASP upgrades textual skills into executable Program Functions that intervene in LLM agent loops at inference, post-training, or self-evolution, delivering 25% gains over ReAct and 30.4% over Search-R1 on reasoning benchmarks.
-
Self-Supervised On-Policy Distillation for Reasoning Language Models
SSOPD converts intra-group correct-wrong contrast into process supervision by distilling a teacher distribution from the shortest correct completion into prefixes of the longest wrong completion, improving GRPO on AIME and HMMT benchmarks.
-
Dynamic Model Merging Made Slim
DiDi-Merging achieves dynamic model merging performance matching or exceeding prior methods while using only 1.24x to 1.4x the parameters of a single fine-tuned model.
-
Task Abstention for Large Language Models in Code Generation
A distribution-free abstention rule grounded in multiple hypothesis testing uses execution consistency to let code LLMs avoid hallucination-prone tasks with theoretical guarantees.
-
Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers
Diffusion LLMs can act as their own efficiency teachers by using revokable parallel decoding to identify reliable token orders and then distilling those orders into the model parameters for faster inference.
-
PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play
PopuLoRA shows that co-evolving populations of LoRA adapters through cross-evaluated self-play can outperform compute-matched single-agent baselines on multiple code and math reasoning benchmarks.
-
Asking Back: Interaction-Layer Antidistillation Watermarks
Interaction-layer antidistillation watermarks use system-prompt-induced behavioral markers like explicit follow-up questions that transfer to distilled student models at 45-89% relative fidelity and can be audited via black-box LLM-as-judge queries.
-
See Before You Code: Learning Visual Priors for Spatially Aware Educational Animation Generation
OmniManim improves render quality in educational animation code generation by using a Vision Agent with coarse-to-fine bounding-box denoising and interpolation-aware optimization on new datasets.
-
GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero
GRLO shows RLHF from scratch on 5K open-ended prompts raises average performance from 24.1 to 63.1 across domains on Qwen3-4B-Base using 46x less data and 68x less compute than in-domain RLVR while remaining competitive with heavily post-trained models.
-
Viverra: Text-to-Code with Guarantees
Viverra generates C code from text descriptions together with assertions that are verified by model checkers, and a user study with over 400 participants shows the verified assertions improve code comprehension.
-
Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation
On-policy self-distillation with teacher flip rate yields better safety-reasoning tradeoffs than off-policy or external-teacher baselines across model scales.
-
PreFT: Prefill-only finetuning for efficient inference
Prefill-only adaptation of LLMs yields 1.9x higher throughput for 512 adapters on Llama 3.1 70B with near-parity performance on RL tasks and recoverable loss on SFT.
-
Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation
Local teachability collapse occurs in later trajectory segments during strong-to-weak OPD; a margin-based release rule using top-K teacher advantage and BIC change-point detection on sentence segments outperforms full-trajectory supervision on five in-domain benchmarks and preserves out-of-domain pe
-
CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution
CANTANTE uses contrastive rollouts to attribute system rewards to individual agents, enabling better prompt optimization than prior methods on programming, math, and QA benchmarks.
-
When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems
A wrapper for black-box generate-verify AI pipelines that uses a conservative hard-negative reference pool and e-processes to control the probability of releasing on infeasible tasks while permitting release on feasible ones.
-
Bayesian Model Merging
Bayesian Model Merging introduces a bi-level optimization framework that merges task-specific models via closed-form Bayesian regression with an anchor prior and global hyperparameter search, outperforming baselines and nearly matching expert averages on up to 20-task vision and 5-task language Merg
-
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
Orthrus unifies autoregressive LLMs and diffusion models via shared KV cache and consensus to enable up to 7.8x parallel token generation speedup with O(1) memory overhead and lossless results.
-
Uncertainty Quantification for LLM-based Code Generation
RisCoSet applies multiple hypothesis testing to construct risk-controlling partial-program prediction sets for LLM code generation, achieving up to 24.5% less code removal than prior methods at equivalent risk levels.
-
gwBenchmarks: Stress-Testing LLM Agents on High-Precision Gravitational Wave Astronomy
LLM coding agents cannot reach the 10^{-4} relative accuracy required for gravitational wave modeling tasks and show systematic failures including metric misuse and result fabrication.
-
Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning
METIS internalizes curriculum judgment in LLM reinforcement fine-tuning by predicting within-prompt reward variance via in-context learning and jointly optimizing with a self-judgment reward, yielding superior performance and up to 67% faster convergence across math, code, and agent benchmarks.
-
DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices
DECO is a sparse MoE architecture with ReLU-based routing, learnable expert scaling, and NormSiLU activation that matches dense Transformer performance at 20% expert activation and delivers 2.93x speedup on Jetson AGX Orin.
-
Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
QD-LLM applies neuroevolution to prompt embeddings within a quality-diversity framework, producing 46% higher coverage and 41% higher QD-score than QDAIF on HumanEval, MBPP, and creative writing benchmarks.
-
Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training
Forgetting in LLM continual post-training is a geometry conflict between task-induced covariance structures and the evolving model state, controlled by gating Wasserstein barycenter merging on measured conflict.
-
Edit-Based Refinement for Parallel Masked Diffusion Language Models
ME-DLM augments parallel masked diffusion models with edit-distance-supervised refinements to raise quality on coding and math benchmarks while using far fewer diffusion steps.
-
DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
DARE co-evolves difficulty estimation and policy in RL for LLMs to improve training efficiency, final performance, and inference speed by using tailored strategies for different difficulty levels.
-
BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
BoostAPR boosts automated program repair by training a sequence-level assessor and line-level credit allocator from execution outcomes, then applying them in PPO to reach 40.7% on SWE-bench Verified.
-
Evaluating LLM-Generated Code: A Benchmark and Developer Study
Introduces a three-fold benchmark for LLM-generated code combining correctness testing on a complex project, quality verification, and developer surveys to assess production readiness.
-
Using Semantic Distance to Estimate Uncertainty in LLM-Based Code Generation
Semantic distance on program execution behaviors improves uncertainty estimation for LLM code generation and outperforms prior sample-based methods across benchmarks and models.
-
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
OPT-BENCH and OPT-Agent evaluate LLM self-optimization in large search spaces, showing stronger models improve via feedback but stay constrained by base capacity and below human performance.
-
VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation
VeriContest supplies 946 problems with specs, code, proofs, and tests to benchmark verifiable code generation in Rust/Verus, showing models reach 92% on code but only 5% end-to-end on full verifiable synthesis.
-
AIPO: Learning to Reason from Active Interaction
AIPO adds active multi-agent consultation (Verify, Knowledge, Reasoning agents) plus custom importance sampling to RLVR training so LLMs expand their reasoning boundary and then operate without the agents.
-
SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution
SWE Atlas is a benchmark suite for coding agents that evaluates Codebase Q&A, Test Writing, and Refactoring using comprehensive protocols assessing both functional correctness and software engineering quality.
-
SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation
SimCT enlarges the supervision space in cross-tokenizer on-policy distillation using short jointly tokenizable multi-token continuations, producing consistent gains over shared-token baselines on math and code benchmarks.
-
PaT: Planning-after-Trial for Efficient Test-Time Code Generation
PaT defers planning until after failed trials in LLM code generation, enabling heterogeneous cheap-plus-powerful model setups that match large-model performance at roughly 69% lower cost.