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%).
416
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 57
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
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.
Signature filtering learns unreliable tokens with MILP and removes them at detection time, raising true positive rates from 8-31% to 78-99% across Kgw, Sweet, Unigram, and Exp watermarks on multiple corpora and LLMs while controlling false positives.
3DCodeBench is a new benchmark evaluating 12 VLMs on translating multimodal prompts into procedural 3D modeling code, paired with 3DCodeArena for human preference rankings.
Sakura is a multi-agent system that generates structurally complex tests from NL descriptions, achieving 50-78% higher compilability and 38-66% higher coverage overlap than baselines on 1,464 scenarios from 20 Apache Commons applications.
TAPS converts diffusion marginal probabilities into path-conditioned acceptance estimates to select prefix-closed subtrees under a fixed verification budget, achieving up to 7.9x end-to-end speedup over autoregressive decoding.
D³ introduces a dynamic directional graph-constrained framework that models sample interactions via loss dependencies to derive an optimized training sequence for LLMs.
An empirical study of 547 confirmed safety incidents from GitHub and literature derives a 33-type taxonomy showing constraint violations, destructive actions, and deception dominate in everyday coding-agent use.
BASTION is a budget-aware speculative decoding framework with adaptive tree-structured block diffusion drafting that reports up to 6.61x speedup and 39% improvement over block-diffusion baselines.
BrahmicTokenizer-131K is a 131K-vocab tokenizer constructed via script-prune crop and linear-programming retrofit to o200k_base, achieving 26.7% fewer tokens on Indic text while matching o200k_base on English fertility and outperforming alternatives on code/math benchmarks.
Logit composition of autoregressive models is projective under factorized conditionals, preserved under smooth reparameterizations, and maintains length generalization when assumptions hold uniformly.
RepoMirage uses semantics-preserving perturbations on SWE-Bench to show code agents lack repository context reasoning, with performance falling sharply on extended structure tasks, and introduces RepoAnchor as a structure-first fix.
citing papers explorer
-
PDEAgent-Bench: A Multi-Metric, Multi-Library Benchmark for PDE Solver Generation
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: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
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.
-
Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark
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.
-
TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding
TAPS converts diffusion marginal probabilities into path-conditioned acceptance estimates to select prefix-closed subtrees under a fixed verification budget, achieving up to 7.9x end-to-end speedup over autoregressive decoding.
-
BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems
BOHM extracts multi-resolution attribution trees from existing routing weights in hierarchical AI systems, providing zero-cost explanations that correlate with SHAP when routing is near-optimal.
-
WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games
WebGameBench is a new benchmark that evaluates coding agents on building browser-native games from frozen specifications, with runtime browser evaluation showing best agents reach 76.9% usable rate but only 20.2% excellent rate.
-
EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
EVOCHAMBER enables test-time co-evolution of multi-agent systems across three scales, producing emergent niche specialists and performance gains of up to 32% relative on math tasks with Qwen3-8B.
-
Prospective Compression in Human Abstraction Learning
Humans exhibit abstraction learning consistent with prospective compression of future tasks in non-stationary domains, unlike retrospective compression algorithms or LLM-based approaches.
-
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.
-
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.
-
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.
-
ContractEval: A Benchmark for Evaluating Contract-Satisfying Assertions in Code Generation
ContractEval benchmark on 364 tasks shows code LLMs achieve 75-82% functional pass@1 but 0% contract satisfaction under standard prompting, rising only to 23-41% with explicit contracts.
-
Reflexion: Language Agents with Verbal Reinforcement Learning
Reflexion lets LLM agents improve via stored verbal reflections on task feedback, reaching 91% pass@1 on HumanEval and outperforming prior GPT-4 results.
-
Agent-as-a-Router: Agentic Model Routing for Coding Tasks
Agent-as-a-Router turns static LLM routing into an iterative C-A-F loop that accumulates execution feedback to lower cumulative regret on coding tasks.
-
ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment
ANDES equips AI agents with an interactive data-synthesis skill using World Tree routing to reach SOTA automated alignment on PostTrainBench under compute limits.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.
-
Trace-Level Analysis of Information Contamination in Multi-Agent Systems
Agent workflows can diverge substantially from contaminated inputs yet recover correct answers, or stay similar while failing, as measured by trace divergence on GAIA tasks.
-
When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling
A disagreement-guided routing framework dynamically selects among resolution, voting, and rewriting strategies for test-time scaling, delivering 3-7% accuracy gains with lower sampling cost on mathematical benchmarks.
-
Weight Patching: Toward Source-Level Mechanistic Localization in LLMs
Weight Patching localizes capabilities to specific parameter modules in LLMs by replacing weights from a behavior-specialized model into a base model and validating recovery via a vector-anchor interface, revealing a hierarchy of source, routing, and execution components.
-
AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction
AgentXRay formulates workflow reconstruction as combinatorial optimization and uses Monte Carlo Tree Search with Red-Black Pruning to approximate black-box agent behaviors via output-based proxy metrics.
-
Token-Level LLM Collaboration via FusionRoute
FusionRoute augments token-level expert routing with a trainable complementary logit generator to expand the policy class and recover optimal decoding under mild conditions, outperforming prior collaboration and merging methods on reasoning and generation benchmarks.
-
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Math reasoning gains in LLMs rarely transfer to general domains; RL tuning generalizes while SFT causes forgetting and representation drift.
-
Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
A learned orchestration policy for LLM agents that jointly optimizes task decomposition and selective routing to (model, primitive) pairs, delivering 77% macro pass@1 at 10x lower cost than strong baselines across 13 benchmarks.
-
Tree of Thoughts as a Classical Heuristic Search Problem: Formal Foundations and Design Patterns
Synthesizes existing Tree-of-Thoughts work into a unified taxonomy using classical heuristic search terminology and identifies design patterns across shallow and deep reasoning tasks.
-
Latent Action Reparameterization for Efficient Agent Inference
LAR learns a compact latent action space from trajectories that shortens the effective decision horizon for LLM agents, reducing token count and inference time while preserving task success.
-
Interactive Evaluation Requires a Design Science
Interactive evaluation of AI must be reframed as a distinct paradigm that maps interaction trajectories to judgments on process, recoverability, coordination, robustness, and system performance, supported by a two-axis taxonomy and design principles.
-
HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory
HyperLens reveals that deeper transformer layers magnify small confidence changes into fine-grained trajectories, allowing quantification of cognitive effort where complex tasks demand more and standard SFT can reduce it.
-
RESCORE: LLM-Driven Simulation Recovery in Control Systems Research Papers
RESCORE recovers task-coherent simulations from 40.7% of 500 CDC papers via a three-component LLM agent pipeline and claims a 10X speedup over manual human replication.
-
AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
-
DeepSeek-VL: Towards Real-World Vision-Language Understanding
DeepSeek-VL develops open-source 1.3B and 7B vision-language models that achieve competitive or state-of-the-art results on real-world visual-language benchmarks through diverse data curation, a hybrid vision encoder, and pretraining that preserves language capabilities.
-
Submodular Benchmark Selection
Submodular maximization under a Gaussian model selects small benchmark subsets that outperform random selection for imputing leaderboard scores, with mutual information better than entropy at small sizes.
-
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
The paper surveys reinforced reasoning techniques for LLMs, covering automated data construction, learning-to-reason methods, and test-time scaling as steps toward Large Reasoning Models.
- Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps
- Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards
- Prompt Optimization Is a Coin Flip: Diagnosing When It Helps in Compound AI Systems
- VeRO: A Harness for Agents to Optimize Agents
- Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic
- Language Model Networks: Supervision-Efficient Learning through Dense Communication