A survey that unifies prior work on multi-agent LLM systems via the LIFE framework, mapping dependencies across collaboration, failure attribution, and autonomous self-evolution while identifying cross-stage challenges.
hub Mixed citations
Metatool benchmark for large language models: Deciding whether to use tools and which to use
Mixed citation behavior. Most common role is background (67%).
17
Pith papers citing it
Background
67% of classified citations
hub tools
citation-role summary
background 7
dataset 2
citation-polarity summary
representative citing papers
Model-adaptive tool necessity shows 26-54% mismatch with actual tool calls across LLMs, driven by nearly orthogonal hidden-state signals for cognition versus action.
LLM agents reach only 50.6% accuracy on chemical cost estimation within 25% error even with tools, dropping with noise due to parsing, pack selection, and tool-use failures.
τ²-bench provides a Dec-POMDP-based telecom domain with compositional task generation and a tool-constrained user simulator to measure agent performance drops in dual-control versus single-control settings.
ToolHijacker optimizes malicious tool documents via a two-phase strategy to hijack LLM agents' tool selection in no-box settings.
τ-bench shows state-of-the-art agents like GPT-4o succeed on under 50% of tool-using, rule-following tasks and are inconsistent across repeated trials.
Maestro uses outcome-based RL to train a lightweight policy that orchestrates ensembles of frozen expert models and skills, reporting 70.1% average accuracy across ten multimodal benchmarks and outperforming GPT-5 and Gemini-2.5-Pro while generalizing to unseen components.
FitText embeds memetic evolutionary retrieval inside the agent's reasoning loop to iteratively refine pseudo-tool descriptions, raising retrieval rank from 8.81 to 2.78 on ToolRet and pass rate to 0.73 on StableToolBench.
The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.
A framework automates multi-agent system creation via LLM planning and two-stage agent recommendation, claiming higher recall than prior methods.
A hybrid deterministic-plus-semantic interception layer for continuous task-based authorization of multi-turn LLM agent tool invocations, with new multi-turn datasets and initial experiments.
LLM agents exhibit temporal blindness, achieving no better than 65% normalized alignment with human preferences on tool-use decisions across time-sensitive scenarios in the new TicToc dataset.
TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt utility.
The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.
citing papers explorer
-
Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
A survey that unifies prior work on multi-agent LLM systems via the LIFE framework, mapping dependencies across collaboration, failure attribution, and autonomous self-evolution while identifying cross-stage challenges.
-
Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
Model-adaptive tool necessity shows 26-54% mismatch with actual tool calls across LLMs, driven by nearly orthogonal hidden-state signals for cognition versus action.
-
Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning
LLM agents reach only 50.6% accuracy on chemical cost estimation within 25% error even with tools, dropping with noise due to parsing, pack selection, and tool-use failures.
-
$\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
τ²-bench provides a Dec-POMDP-based telecom domain with compositional task generation and a tool-constrained user simulator to measure agent performance drops in dual-control versus single-control settings.
-
Prompt Injection Attack to Tool Selection in LLM Agents
ToolHijacker optimizes malicious tool documents via a two-phase strategy to hijack LLM agents' tool selection in no-box settings.
-
$\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
τ-bench shows state-of-the-art agents like GPT-4o succeed on under 50% of tool-using, rule-following tasks and are inconsistent across repeated trials.
-
Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles
Maestro uses outcome-based RL to train a lightweight policy that orchestrates ensembles of frozen expert models and skills, reporting 70.1% average accuracy across ten multimodal benchmarks and outperforming GPT-5 and Gemini-2.5-Pro while generalizing to unseen components.
-
FitText: Evolving Agent Tool Ecologies via Memetic Retrieval
FitText embeds memetic evolutionary retrieval inside the agent's reasoning loop to iteratively refine pseudo-tool descriptions, raising retrieval rank from 8.81 to 2.78 on ToolRet and pass rate to 0.73 on StableToolBench.
-
Memory in the Age of AI Agents
The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.
-
GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.
-
From Intent to Execution: Composing Agentic Workflows with Agent Recommendation
A framework automates multi-agent system creation via LLM planning and two-stage agent recommendation, claiming higher recall than prior methods.
-
Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AI
A hybrid deterministic-plus-semantic interception layer for continuous task-based authorization of multi-turn LLM agent tool invocations, with new multi-turn datasets and initial experiments.
-
Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception
LLM agents exhibit temporal blindness, achieving no better than 65% normalized alignment with human preferences on tool-use decisions across time-sensitive scenarios in the new TicToc dataset.
-
TrustLLM: Trustworthiness in Large Language Models
TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt utility.
-
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.
- To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling
- Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents