TraceFix repairs LLM-generated multi-agent protocols via TLA+ counterexamples to achieve full verification on all tested tasks and higher completion rates than prompt-only baselines.
Canonical reference
Title resolution pending
Canonical reference. 86% of citing Pith papers cite this work as background.
26
Pith papers citing it
Background
86% of classified citations
citation-role summary
background 6
method 1
citation-polarity summary
representative citing papers
DynamicUI improves GUI agent performance in high-dynamic environments by processing interaction videos with frame clustering, action-conditioned refinement, and reflection, outperforming prior approaches on the new DynamicGUIBench spanning ten applications.
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).
LLM agents reach only 35% average checkpoint completion on ten realistic CTF challenges in a new open benchmark with automated partial-credit scoring.
AgenTEE isolates LLM agent runtime, inference, and apps in independently attested cVMs on Arm-based edge devices, achieving under 5.15% overhead versus commodity OS deployments.
SAGE is a new multi-agent benchmark that formalizes service SOPs as dynamic dialogue graphs to measure LLM agents on logical compliance and path coverage, uncovering an execution gap and empathy resilience across 27 models in 6 scenarios.
AgentSZZ is an LLM-agent framework that identifies bug-inducing commits with up to 27.2% higher F1 scores than prior methods by enabling adaptive exploration and causal tracing, especially for cross-file and ghost commits.
Agentic search narrows the gap between dense RAG and GraphRAG but does not remove GraphRAG's advantage on complex multi-hop reasoning.
VLegal-Bench supplies 10,450 expert-validated samples for evaluating LLMs on Vietnamese legal questions, retrieval, multi-step reasoning, and scenario solving.
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.
SnapGuard detects prompt injection attacks on screenshot-based web agents via visual stability indicators and contrast-polarity textual signals, reaching F1 0.75 while running 8x faster than GPT-4o with no added memory cost.
Hive is a multi-agent infrastructure with a logits cache for reducing cross-path redundancy in sampling and agent-aware scheduling for better compute and KV-cache allocation, shown to deliver 1.11x-1.76x speedups and 33%-51% lower hotspot miss rates.
Scepsy schedules arbitrary multi-LLM agentic workflows on GPU clusters by constructing Aggregate LLM Pipelines from stable per-LLM execution time shares, then searching fractional GPU allocations, tensor parallelism, and replica counts to achieve up to 2.4x higher throughput and 27x lower latency.
ACGM learns task-adaptive sparse graphs over multi-modal agent histories via policy-gradient optimization, reaching 82.7 nDCG@10 and 89.2% Precision@10 on WebShop, VisualWebArena, and Mind2Web while outperforming 19 baselines.
ForkKV uses copy-on-write disaggregated KV cache with DualRadixTree and ResidualAttention kernels to deliver up to 3x throughput over prior multi-LoRA serving systems with negligible quality loss.
More fault localization context does not consistently improve LLM-based program repair; file-level context gives 15-17x gains, optimal around 6-10 files, while line-level context often degrades performance from noise.
EASP adds a Probe-then-Plan step so LLMs ground their search plans in actual retrieval snapshots and inventory, yielding higher recall and business metrics in sub-second production search.
CiteAudit supplies a human-validated benchmark and multi-agent verification system that outperforms existing LLMs and commercial tools at detecting hallucinated scientific references.
SKG-VLA models each complaint as a structured scene via a Scene Knowledge Graph to improve policy-grounded multimodal reasoning and decision accuracy.
SAKE is an agentic framework for GMNER that uses uncertainty-based self-awareness and reinforcement learning to balance internal knowledge exploitation with adaptive external exploration.
LLM agents enable a shift in recommender systems from opaque hidden profiles to governable, inspectable, and portable user representations.
DDAP is a controlled agentic framework that guides non-experts via four LLM-assisted stages to construct competitive AI pipelines for business, biology, and health domains.
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.
VisionClaw couples continuous egocentric vision on smart glasses with speech-driven AI agents to enable hands-free real-world tasks, with lab and field studies showing faster completion and a shift toward opportunistic delegation.
citing papers explorer
-
TraceFix: Repairing Agent Coordination Protocols with TLA+ Counterexamples
TraceFix repairs LLM-generated multi-agent protocols via TLA+ counterexamples to achieve full verification on all tested tasks and higher completion rates than prompt-only baselines.
-
Benchmarking and Improving GUI Agents in High-Dynamic Environments
DynamicUI improves GUI agent performance in high-dynamic environments by processing interaction videos with frame clustering, action-conditioned refinement, and reflection, outperforming prior approaches on the new DynamicGUIBench spanning ten applications.
-
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).
-
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.
-
AgenTEE: Confidential LLM Agent Execution on Edge Devices
AgenTEE isolates LLM agent runtime, inference, and apps in independently attested cVMs on Arm-based edge devices, achieving under 5.15% overhead versus commodity OS deployments.
-
SAGE: A Service Agent Graph-guided Evaluation Benchmark
SAGE is a new multi-agent benchmark that formalizes service SOPs as dynamic dialogue graphs to measure LLM agents on logical compliance and path coverage, uncovering an execution gap and empathy resilience across 27 models in 6 scenarios.
-
AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits
AgentSZZ is an LLM-agent framework that identifies bug-inducing commits with up to 27.2% higher F1 scores than prior methods by enabling adaptive exploration and causal tracing, especially for cross-file and ghost commits.
-
Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems
Agentic search narrows the gap between dense RAG and GraphRAG but does not remove GraphRAG's advantage on complex multi-hop reasoning.
-
VLegal-Bench: Cognitively Grounded Benchmark for Vietnamese Legal Reasoning of Large Language Models
VLegal-Bench supplies 10,450 expert-validated samples for evaluating LLMs on Vietnamese legal questions, retrieval, multi-step reasoning, and scenario solving.
-
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.
-
SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents
SnapGuard detects prompt injection attacks on screenshot-based web agents via visual stability indicators and contrast-polarity textual signals, reaching F1 0.75 while running 8x faster than GPT-4o with no added memory cost.
-
Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling
Hive is a multi-agent infrastructure with a logits cache for reducing cross-path redundancy in sampling and agent-aware scheduling for better compute and KV-cache allocation, shown to deliver 1.11x-1.76x speedups and 33%-51% lower hotspot miss rates.
-
Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines
Scepsy schedules arbitrary multi-LLM agentic workflows on GPU clusters by constructing Aggregate LLM Pipelines from stable per-LLM execution time shares, then searching fractional GPU allocations, tensor parallelism, and replica counts to achieve up to 2.4x higher throughput and 27x lower latency.
-
Task-Adaptive Retrieval over Agentic Multi-Modal Web Histories via Learned Graph Memory
ACGM learns task-adaptive sparse graphs over multi-modal agent histories via policy-gradient optimization, reaching 82.7 nDCG@10 and 89.2% Precision@10 on WebShop, VisualWebArena, and Mind2Web while outperforming 19 baselines.
-
ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache
ForkKV uses copy-on-write disaggregated KV cache with DualRadixTree and ResidualAttention kernels to deliver up to 3x throughput over prior multi-LoRA serving systems with negligible quality loss.
-
On the Role of Fault Localization Context for LLM-Based Program Repair
More fault localization context does not consistently improve LLM-based program repair; file-level context gives 15-17x gains, optimal around 6-10 files, while line-level context often degrades performance from noise.
-
Probe-then-Plan: Environment-Aware Planning for Industrial E-commerce Search
EASP adds a Probe-then-Plan step so LLMs ground their search plans in actual retrieval snapshots and inventory, yielding higher recall and business metrics in sub-second production search.
-
CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era
CiteAudit supplies a human-validated benchmark and multi-agent verification system that outperforms existing LLMs and commercial tools at detecting hallucinated scientific references.
-
SKG-VLA: Scene Knowledge Graph Priors for Structured Scene Semantics and Multimodal Reasoning for Decision Making
SKG-VLA models each complaint as a structured scene via a Scene Knowledge Graph to improve policy-grounded multimodal reasoning and decision accuracy.
-
SAKE: Self-aware Knowledge Exploitation-Exploration for Grounded Multimodal Named Entity Recognition
SAKE is an agentic framework for GMNER that uses uncertainty-based self-awareness and reinforcement learning to balance internal knowledge exploitation with adaptive external exploration.
-
From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents
LLM agents enable a shift in recommender systems from opaque hidden profiles to governable, inspectable, and portable user representations.
-
From Intent to AI Pipelines: A Controlled Agentic Framework for Non-AI Expert Scientists
DDAP is a controlled agentic framework that guides non-experts via four LLM-assisted stages to construct competitive AI pipelines for business, biology, and health domains.
-
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.
-
VisionClaw: Always-On AI Agents through Smart Glasses
VisionClaw couples continuous egocentric vision on smart glasses with speech-driven AI agents to enable hands-free real-world tasks, with lab and field studies showing faster completion and a shift toward opportunistic delegation.
-
ActionNex: A Virtual Outage Manager for Cloud Computing
ActionNex is an agentic system for cloud outage management that compresses multimodal signals into critical events, uses hierarchical memory for reasoning, and recommends actions with 71.4% precision on real Azure outages.
- VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning