CAI Dataset is presented as the largest described corpus of LLM-driven hacker trajectories, with the claim that operator data concentration in frontier-model providers creates a major security risk best addressed by on-premise specialized LLMs.
hub
ToolACE : Winning the points of LLM function calling
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
hub tools
citation-role summary
background 2
dataset 1
citation-polarity summary
representative citing papers
RubricRefine is a training-free pre-execution method that creates rubrics to score and fix inter-tool contract violations in agent code, reaching 0.86 average on M3ToolEval across seven models with zero executions and lower latency.
MAD-OPD recasts on-policy distillation teachers as a debating collective to supply better supervision, lifting agentic and code performance over single-teacher OPD across multiple model sizes.
Q-ARE dataset and metrics reveal that existing API recommendation methods and LLMs degrade sharply on multi-level invocation chains.
COVERT generates verifiable synthetic tool-use environments for RL by validated trajectory synthesis and oracle-preserving augmentations, improving tool-use accuracy on BFCL v3 and ACEBench while remaining complementary to SFT.
ToolPRM provides fine-grained intra-call process supervision via a new dataset and reward model, outperforming outcome and coarse-grained alternatives on function-calling benchmarks.
Tool-calling evaluations for LLM agents are highly sensitive to implementation details such as random seeds and history handling, and two new techniques accelerate RL training with wall-clock speedup and no performance degradation.
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.
CuraView detects sentence-level faithfulness hallucinations in medical discharge summaries via GraphRAG knowledge graphs and multi-agent evidence grading, achieving 0.831 F1 on critical contradictions with a fine-tuned Qwen3-14B model and 50% relative improvement over baselines.
A two-stage multi-agent LLM converts structural inputs to JSON then platform-specific scripts for ETABS, SAP2000, and OpenSees, achieving over 90% accuracy on 20 frame problems across ten trials.
ATBench is a new trajectory-level benchmark with 1,000 diverse and realistic scenarios for assessing safety in LLM agents.
GDPO decouples per-reward normalization in multi-reward RL to avoid advantage collapse and improve convergence over GRPO on tool-calling, math, and coding tasks.
A principled reward design for tool selection and application in RL-trained LLMs delivers 17% gains over base models and 15% over SFT across benchmarks.
LOM-action uses business events to drive ontology-governed graph simulations that generate auditable decisions, reporting 93.82% accuracy and 98.74% tool-chain F1 versus 24-36% F1 for frontier LLMs.
ALTK supplies reusable middleware components that systematically address failure modes across the full AI agent lifecycle from request to response.
Structured reflection makes error diagnosis and repair an explicit trainable step that improves reliability and reduces redundant calls in tool-using LLM agents.
Analysis of ClawHub shows language-based functional divides in agent skills, with over 30% flagged suspicious and submission-time documentation enabling 73% accurate risk prediction.
citing papers explorer
-
Cybersecurity AI (CAI) Dataset
CAI Dataset is presented as the largest described corpus of LLM-driven hacker trajectories, with the claim that operator data concentration in frontier-model providers creates a major security risk best addressed by on-premise specialized LLMs.
-
RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement
RubricRefine is a training-free pre-execution method that creates rubrics to score and fix inter-tool contract violations in agent code, reaching 0.86 average on M3ToolEval across seven models with zero executions and lower latency.
-
MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate
MAD-OPD recasts on-policy distillation teachers as a debating collective to supply better supervision, lifting agentic and code performance over single-teacher OPD across multiple model sizes.
-
Q-ARE: An Evaluation Dataset for Query Based API Recommendation
Q-ARE dataset and metrics reveal that existing API recommendation methods and LLMs degrade sharply on multi-level invocation chains.
-
Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning
COVERT generates verifiable synthetic tool-use environments for RL by validated trajectory synthesis and oracle-preserving augmentations, improving tool-use accuracy on BFCL v3 and ACEBench while remaining complementary to SFT.
-
ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling
ToolPRM provides fine-grained intra-call process supervision via a new dataset and reward model, outperforming outcome and coarse-grained alternatives on function-calling benchmarks.
-
On Effectiveness and Efficiency of Agentic Tool-calling and RL Training
Tool-calling evaluations for LLM agents are highly sensitive to implementation details such as random seeds and history handling, and two new techniques accelerate RL training with wall-clock speedup and no performance degradation.
-
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.
-
CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification
CuraView detects sentence-level faithfulness hallucinations in medical discharge summaries via GraphRAG knowledge graphs and multi-agent evidence grading, achieving 0.831 F1 on critical contradictions with a fine-tuned Qwen3-14B model and 50% relative improvement over baselines.
-
Automating Structural Analysis Across Multiple Software Platforms Using Large Language Models
A two-stage multi-agent LLM converts structural inputs to JSON then platform-specific scripts for ETABS, SAP2000, and OpenSees, achieving over 90% accuracy on 20 frame problems across ten trials.
-
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
ATBench is a new trajectory-level benchmark with 1,000 diverse and realistic scenarios for assessing safety in LLM agents.
-
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
GDPO decouples per-reward normalization in multi-reward RL to avoid advantage collapse and improve convergence over GRPO on tool-calling, math, and coding tasks.
-
ToolRL: Reward is All Tool Learning Needs
A principled reward design for tool selection and application in RL-trained LLMs delivers 17% gains over base models and 15% over SFT across benchmarks.
-
From Business Events to Auditable Decisions: Ontology-Governed Graph Simulation for Enterprise AI
LOM-action uses business events to drive ontology-governed graph simulations that generate auditable decisions, reporting 93.82% accuracy and 98.74% tool-chain F1 versus 24-36% F1 for frontier LLMs.
-
Agent Lifecycle Toolkit (ALTK): Reusable Middleware Components for Robust AI Agents
ALTK supplies reusable middleware components that systematically address failure modes across the full AI agent lifecycle from request to response.
-
Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions
Structured reflection makes error diagnosis and repair an explicit trainable step that improves reliability and reduces redundant calls in tool-using LLM agents.
-
Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub
Analysis of ClawHub shows language-based functional divides in agent skills, with over 30% flagged suspicious and submission-time documentation enabling 73% accurate risk prediction.
- R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling