SmoothAgent introduces lookahead context engineering to eliminate transformation overhead in LLM agents, reducing TTFT by up to 11.9x through proactive KV cache preparation.
Title resolution pending
27 Pith papers cite this work. Polarity classification is still indexing.
27
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
JETO-Mine and JETO-Bench provide a configurable, Docker-based pipeline and dataset of 91 verified Java execution-time improvement patches, on which OpenHands fixes 13 of 91 issues (14.3%).
Rover uses a new Multi-layer Code Property Graph and clustering to supply LLMs with dependency-aware contexts, outperforming standalone LLMs, MergeGen, and WizardMerge on similarity to ground-truth conflict resolutions.
CppPerf-Mine produces CppPerf-DB, a benchmark of 347 real-world performance-improving C++ patches (39% multi-file) from 42 repositories to evaluate repository-level repair tools.
ADI equips AI debugging agents with function-level interaction via a new execution trace structure, raising SWE-bench Verified resolution to 63.8% at $1.28 per task and delivering 6-18% gains when added to existing agents.
LLMVD.js uses LLM agents to confirm 84% of taint-style vulnerabilities on public benchmarks (vs. <22% for prior tools) and generates validated exploits for 36 of 260 new packages (vs. ≤2 for traditional tools).
PlayCoder raises the rate of LLM-generated GUI apps that can be played end-to-end without logic errors from near zero to 20.3% Play@3 by adding repository-aware generation, agent-driven testing, and iterative repair.
LLM agents reach only 35% average checkpoint completion on ten realistic CTF challenges in a new open benchmark with automated partial-credit scoring.
LogicLoc combines LLMs with Datalog to achieve accurate repo-level code localization without relying on keyword shortcuts in benchmarks.
A large-scale empirical study categorizes bugs in LLM agents and demonstrates that a specialized LLM agent can annotate them accurately at very low cost.
SWE-QA creates a new repository-level code QA benchmark with 576 pairs and an agentic LLM framework, showing promise but open challenges for models handling complex codebases.
OrchestrXR uses multi-agent orchestration with structured schemas to generate Unity XR study prototypes from ideas, supported by a user study with 12 researchers indicating effective support and intent preservation.
ClarifyCodeBench is a new benchmark with manual annotations and two metrics showing that LLMs strong at code generation are weak at clarifying ambiguous requirements, with performance worsening as ambiguity density rises.
CoHiKer improves Top-1 fault localization accuracy in the Linux kernel by up to 26% at file level and 57% at method level over prior LLM baselines via contrastive reasoning and hierarchical context analysis.
MuMuTestUp is a mutation-guided multi-agent framework for updating test cases in evolving software that strengthens assertions via surviving mutants, targets specific coverage gaps, and uses semantic search instead of exact matching.
MemRepair is a hierarchical memory-augmented agent framework that raises repository-level vulnerability repair rates to 58.0-58.2% on Python/Go/JS benchmarks and 30.58% on C++ by combining history, pattern, and refinement memories with iterative feedback.
AOCI creates an incremental symbolic-semantic index per code unit that gives LLMs a complete, consistent repository view, outperforming baselines with zero defects on 19 industrial tasks while using far fewer tokens.
AMMA is a memory-centric multi-chiplet architecture using HBM-PNM cubes, custom logic dies, hybrid parallelism, and reordered collectives that delivers 15.5X lower attention latency and 6.9X lower energy than NVIDIA H100 for 1M context serving.
PrismaDV generates task-aware data unit tests by jointly analyzing downstream code and dataset profiles, outperforming task-agnostic baselines on new benchmarks spanning 60 tasks, with SIFTA enabling automatic prompt optimization that beats hand-written prompts.
PlayCoder combines a repository-aware coding agent with a vision-based GUI testing agent and an automated program repair loop to detect and fix silent logic errors in LLM-generated interactive application code.
GALA uses hierarchical graph alignment between UI screenshots and code structures to achieve state-of-the-art bug localization in multimodal automated program repair on SWE-bench.
REAgent improves LLM patch generation for software issues by 17.4% on average through automated construction, quality checking, and iterative refinement of structured issue-oriented requirements.
Agent-CoEvo is a multi-agent LLM framework that coevolves code patches and test patches to resolve repository-level issues, outperforming fixed-test baselines on SWE-bench Lite and SWT-bench Lite.
ContraFix uses contrastive runtime analysis plus a dual-track skill base to reach 92% resolution on SEC-Bench and 73.8% on PatchEval while improving semantic correctness of patches.
citing papers explorer
-
SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineering
SmoothAgent introduces lookahead context engineering to eliminate transformation overhead in LLM agents, reducing TTFT by up to 11.9x through proactive KV cache preparation.
-
JETO-Bench: A Reproducible Benchmark for Execution Time Improvement Patches in Java
JETO-Mine and JETO-Bench provide a configurable, Docker-based pipeline and dataset of 91 verified Java execution-time improvement patches, on which OpenHands fixes 13 of 91 issues (14.3%).
-
Rover: Context-aware Conflict Resolution with LLM
Rover uses a new Multi-layer Code Property Graph and clustering to supply LLMs with dependency-aware contexts, outperforming standalone LLMs, MergeGen, and WizardMerge on similarity to ground-truth conflict resolutions.
-
CppPerf: An Automated Pipeline and Dataset for Performance-Improving C++ Commits
CppPerf-Mine produces CppPerf-DB, a benchmark of 347 real-world performance-improving C++ patches (39% multi-file) from 42 repositories to evaluate repository-level repair tools.
-
Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis
ADI equips AI debugging agents with function-level interaction via a new execution trace structure, raising SWE-bench Verified resolution to 63.8% at $1.28 per task and delivering 6-18% gains when added to existing agents.
-
Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning
LLMVD.js uses LLM agents to confirm 84% of taint-style vulnerabilities on public benchmarks (vs. <22% for prior tools) and generates validated exploits for 36 of 260 new packages (vs. ≤2 for traditional tools).
-
PlayCoder: Making LLM-Generated GUI Code Playable
PlayCoder raises the rate of LLM-generated GUI apps that can be played end-to-end without logic errors from near zero to 20.3% Play@3 by adding repository-aware generation, agent-driven testing, and iterative repair.
-
Do Agents Dream of Root Shells? Partial-Credit Evaluation of LLM Agents in Capture the Flag Challenges
LLM agents reach only 35% average checkpoint completion on ten realistic CTF challenges in a new open benchmark with automated partial-credit scoring.
-
Neurosymbolic Repo-level Code Localization
LogicLoc combines LLMs with Datalog to achieve accurate repo-level code localization without relying on keyword shortcuts in benchmarks.
-
When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling
A large-scale empirical study categorizes bugs in LLM agents and demonstrates that a specialized LLM agent can annotate them accurately at very low cost.
-
SWE-QA: Can Language Models Answer Repository-level Code Questions?
SWE-QA creates a new repository-level code QA benchmark with 576 pairs and an agentic LLM framework, showing promise but open challenges for models handling complex codebases.
-
OrchestrXR: A Multi-Agent System for Idea-to-Prototype XR Study Authoring
OrchestrXR uses multi-agent orchestration with structured schemas to generate Unity XR study prototypes from ideas, supported by a user study with 12 researchers indicating effective support and intent preservation.
-
ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation
ClarifyCodeBench is a new benchmark with manual annotations and two metrics showing that LLMs strong at code generation are weak at clarifying ambiguous requirements, with performance worsening as ambiguity density rises.
-
Towards Better Linux Kernel Fault Localization: Leveraging Contrastive Reasoning and Hierarchical Context Analysis
CoHiKer improves Top-1 fault localization accuracy in the Linux kernel by up to 26% at file level and 57% at method level over prior LLM baselines via contrastive reasoning and hierarchical context analysis.
-
MuMuTestUp: Mutation-based Multi-Agent Test Case Update
MuMuTestUp is a mutation-guided multi-agent framework for updating test cases in evolving software that strengthens assertions via surviving mutants, targets specific coverage gaps, and uses semantic search instead of exact matching.
-
MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair
MemRepair is a hierarchical memory-augmented agent framework that raises repository-level vulnerability repair rates to 58.0-58.2% on Python/Go/JS benchmarks and 30.58% on C++ by combining history, pattern, and refinement memories with iterative feedback.
-
AOCI: Symbolic-Semantic Indexing for Practical Repository-Scale Code Understanding with LLMs
AOCI creates an incremental symbolic-semantic index per code unit that gives LLMs a complete, consistent repository view, outperforming baselines with zero defects on 19 industrial tasks while using far fewer tokens.
-
AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving
AMMA is a memory-centric multi-chiplet architecture using HBM-PNM cubes, custom logic dies, hybrid parallelism, and reordered collectives that delivers 15.5X lower attention latency and 6.9X lower energy than NVIDIA H100 for 1M context serving.
-
PrismaDV: Automated Task-Aware Data Unit Test Generation
PrismaDV generates task-aware data unit tests by jointly analyzing downstream code and dataset profiles, outperforming task-agnostic baselines on new benchmarks spanning 60 tasks, with SIFTA enabling automatic prompt optimization that beats hand-written prompts.
-
CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
PlayCoder combines a repository-aware coding agent with a vision-based GUI testing agent and an automated program repair loop to detect and fix silent logic errors in LLM-generated interactive application code.
-
GALA: Multimodal Graph Alignment for Bug Localization in Automated Program Repair
GALA uses hierarchical graph alignment between UI screenshots and code structures to achieve state-of-the-art bug localization in multimodal automated program repair on SWE-bench.
-
REAgent: Requirement-Driven LLM Agents for Software Issue Resolution
REAgent improves LLM patch generation for software issues by 17.4% on average through automated construction, quality checking, and iterative refinement of structured issue-oriented requirements.
-
Beyond Fixed Tests: Repository-Level Issue Resolution as Coevolution of Code and Behavioral Constraints
Agent-CoEvo is a multi-agent LLM framework that coevolves code patches and test patches to resolve repository-level issues, outperforming fixed-test baselines on SWE-bench Lite and SWT-bench Lite.
-
ContraFix: Skill-Enhanced Contrastive Runtime Analysis for Vulnerability Repair
ContraFix uses contrastive runtime analysis plus a dual-track skill base to reach 92% resolution on SEC-Bench and 73.8% on PatchEval while improving semantic correctness of patches.
-
HELO-APR: Enhancing Low-Resource Program Repair through Cross-Lingual Knowledge Transfer
HELO-APR uses cross-lingual synthetic data generation and curriculum learning to improve LLM-based automatic program repair in low-resource programming languages.
-
Spec Kit Agents: Context-Grounded Agentic Workflows
A multi-agent SDD framework with phase-level context-grounding hooks improves LLM-judged quality by 0.15 points and SWE-bench Lite Pass@1 by 1.7 percent while preserving near-perfect test compatibility.
-
LLM-Based Automated Diagnosis Of Integration Test Failures At Google
Auto-Diagnose applies LLMs to summarize and diagnose root causes of integration test failures, reporting 90.14% accuracy on 71 manual cases and positive adoption after Google-wide rollout.