LLMs preserve functional behavior in over 91% of generated VeriFast specifications and source code but achieve only 31.4% verification success, with 94% of failures due to separation logic domain knowledge errors.
hub Canonical reference
Repocoder: Repository-level code completion through itera- tive retrieval and generation
Canonical reference. 80% of citing Pith papers cite this work as background.
26
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
method 1
citation-polarity summary
representative citing papers
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.
Constrained Diffusion for Code (CDC) integrates constraint satisfaction into the reverse denoising process of discrete diffusion models via constraint-aware operators that use optimization and program analysis to steer generation toward feasible programs.
Stale repository context in code RAG actively induces models to produce obsolete helper references, raising stale outputs by 76-88 percentage points over current-only retrieval in a 17-sample diagnostic study.
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.
RepoDoc uses a repository knowledge graph with module clustering and semantic impact propagation to generate more complete documentation 3x faster with 85% fewer tokens and handle incremental updates 73% faster than prior LLM-based tools.
PerfCoder is a family of LLMs trained on optimization trajectories with human annotations and runtime-based preference alignment that achieves higher runtime speedups and optimization rates on the PIE benchmark than prior models while producing interpretable feedback.
LLMs propose volatile performance improvements on real-world Java tasks that lag human developers on average, showing algorithmic benchmarks overestimate capabilities.
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
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.
Introduces contextualized code pretraining with caller-callee pairs from static analysis to train CallerGen models that outperform baselines on the new CallerEval benchmark.
XSearch achieves 15x gains on out-of-distribution code search benchmarks by replacing global embedding similarity with explicit concept-to-statement alignment.
SkillLens organizes skills into policies-strategies-procedures-primitives layers, retrieves via degree-corrected random walk, and uses a verifier for local adaptation, yielding up to 6.31 pp gains on MuLocbench and raising ALFWorld success from 45% to 51.31%.
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.
NN-RAG extracts 1,289 candidate neural modules from 19 PyTorch repositories, validates 941 of them, and supplies roughly 72% of the novel structures in the LEMUR dataset while enabling cross-repository migration.
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.
An empirical study finds that injecting call/inheritance topology as comments improves LLM code agent localization by 2.2pp, shortens trajectories by 1.6 rounds, and halves run-to-run variance on medium repositories via a deterministic anchoring effect.
FastContext adds a dedicated exploration subagent with specialized models trained on reference trajectories and task rewards, cutting token consumption up to 60% and lifting resolution rates up to 5.5% on SWE-bench variants.
A Paper-to-Interactive-System Agent and I-WebGenBench benchmark with 19 papers enable converting scientific PDFs into executable interactive web systems, with PaperVoyager framework shown to improve quality.
Function-based chunking underperforms other strategies in RAG code completion by 3.57-5.64 points, with context length as the dominant factor.
RealBench is a repo-level code generation benchmark pairing UML diagrams with natural language requirements, revealing that LLMs perform significantly worse on realistic repo-level tasks than existing benchmarks suggest.
Ablation study finds that a structural codebase index improves localization and resolve rates in coding agents on two SWE benchmarks without raising per-cell cost.
AI labor substitution creates short-term efficiency by masking the erosion of human capability, apprenticeship pipelines, and institutional memory, producing long-term fragility.
Data-influence-score filtering using validation-set loss on downstream coding tasks improves Code-LLM performance, with the most beneficial training data varying significantly across different programming tasks.
citing papers explorer
-
An Empirical Study of LLM-Generated Specifications for VeriFast
LLMs preserve functional behavior in over 91% of generated VeriFast specifications and source code but achieve only 31.4% verification success, with 94% of failures due to separation logic domain knowledge errors.
-
RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
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.
-
Constrained Code Generation with Discrete Diffusion
Constrained Diffusion for Code (CDC) integrates constraint satisfaction into the reverse denoising process of discrete diffusion models via constraint-aware operators that use optimization and program analysis to steer generation toward feasible programs.
-
When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context
Stale repository context in code RAG actively induces models to produce obsolete helper references, raising stale outputs by 76-88 percentage points over current-only retrieval in a 17-sample diagnostic study.
-
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.
-
RepoDoc: A Knowledge Graph-Based Framework to Automatic Documentation Generation and Incremental Updates
RepoDoc uses a repository knowledge graph with module clustering and semantic impact propagation to generate more complete documentation 3x faster with 85% fewer tokens and handle incremental updates 73% faster than prior LLM-based tools.
-
PerfCoder: Large Language Models for Interpretable Code Performance Optimization
PerfCoder is a family of LLMs trained on optimization trajectories with human annotations and runtime-based preference alignment that achieves higher runtime speedups and optimization rates on the PIE benchmark than prior models while producing interpretable feedback.
-
Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software
LLMs propose volatile performance improvements on real-world Java tasks that lag human developers on average, showing algorithmic benchmarks overestimate capabilities.
-
From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
-
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.
-
XSearch: Explainable Code Search via Concept-to-Code Alignment
XSearch achieves 15x gains on out-of-distribution code search benchmarks by replacing global embedding similarity with explicit concept-to-statement alignment.
-
SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents
SkillLens organizes skills into policies-strategies-procedures-primitives layers, retrieves via degree-corrected random walk, and uses a verifier for local adaptation, yielding up to 6.31 pp gains on MuLocbench and raising ALFWorld success from 45% to 51.31%.
-
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.
-
A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks
NN-RAG extracts 1,289 candidate neural modules from 19 PyTorch repositories, validates 941 of them, and supplies roughly 72% of the novel structures in the LEMUR dataset while enabling cross-repository migration.
-
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.
-
How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring
An empirical study finds that injecting call/inheritance topology as comments improves LLM code agent localization by 2.2pp, shortens trajectories by 1.6 rounds, and halves run-to-run variance on medium repositories via a deterministic anchoring effect.
-
FastContext: Training Efficient Repository Explorer for Coding Agents
FastContext adds a dedicated exploration subagent with specialized models trained on reference trajectories and task rewards, cutting token consumption up to 60% and lifting resolution rates up to 5.5% on SWE-bench variants.
-
I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications
A Paper-to-Interactive-System Agent and I-WebGenBench benchmark with 19 papers enable converting scientific PDFs into executable interactive web systems, with PaperVoyager framework shown to improve quality.
-
How Does Chunking Affect Retrieval-Augmented Code Completion? A Controlled Empirical Study
Function-based chunking underperforms other strategies in RAG code completion by 3.57-5.64 points, with context length as the dominant factor.
-
RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices
RealBench is a repo-level code generation benchmark pairing UML diagrams with natural language requirements, revealing that LLMs perform significantly worse on realistic repo-level tasks than existing benchmarks suggest.
-
Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent
Ablation study finds that a structural codebase index improves localization and resolve rates in coding agents on two SWE benchmarks without raising per-cell cost.
-
Short-Term Gain, Long-Term Fragility: AI Labor Substitution and the Erosion of Sustainable Capability
AI labor substitution creates short-term efficiency by masking the erosion of human capability, apprenticeship pipelines, and institutional memory, producing long-term fragility.
-
An Empirical Study on Influence-Based Pretraining Data Selection for Code Large Language Models
Data-influence-score filtering using validation-set loss on downstream coding tasks improves Code-LLM performance, with the most beneficial training data varying significantly across different programming tasks.
-
Qwen2.5-Coder Technical Report
Qwen2.5-Coder models claim state-of-the-art results on over 10 code benchmarks, outperforming larger models of similar size.
-
A Comprehensive Overview of Large Language Models
A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.