Behavioral fingerprints distinguish AI browsing agents from humans and each other, enabling superior detection compared to current bot systems.
hub Canonical reference
The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey
Canonical reference. 91% of citing Pith papers cite this work as background.
31
Pith papers citing it
Background
91% of classified citations
abstract
This survey paper examines the recent advancements in AI agent implementations, with a focus on their ability to achieve complex goals that require enhanced reasoning, planning, and tool execution capabilities. The primary objectives of this work are to a) communicate the current capabilities and limitations of existing AI agent implementations, b) share insights gained from our observations of these systems in action, and c) suggest important considerations for future developments in AI agent design. We achieve this by providing overviews of single-agent and multi-agent architectures, identifying key patterns and divergences in design choices, and evaluating their overall impact on accomplishing a provided goal. Our contribution outlines key themes when selecting an agentic architecture, the impact of leadership on agent systems, agent communication styles, and key phases for planning, execution, and reflection that enable robust AI agent systems.
hub tools
citation-role summary
background 10
baseline 1
citation-polarity summary
representative citing papers
WORC improves multi-agent LLM reasoning to 82.2% average accuracy by predicting and compensating for the weakest agent via targeted extra sampling rather than uniform reinforcement.
GraphBit is a DAG-based engine-orchestrated framework for agentic LLMs that achieves 67.6% accuracy with zero hallucinations on GAIA benchmarks.
Agent-Diff benchmarks LLM agents on enterprise API tasks using code execution and state-diff contracts to define success, evaluated on nine models across 224 tasks with code released.
Empirical study of open-source AI agents shows testing effort concentrates on deterministic tools and workflows (over 70%) while the FM-based plan body gets under 5% and prompts appear in only 1% of tests.
A 7B Qwen-2.5 LLM trained with a new RL framework on only 9 ML tasks achieves performance comparable to much larger proprietary LLM agents at lower computational cost with cross-task generalization.
GRAFT internalizes tool dependency graphs via dedicated special tokens in LLMs and applies on-policy context distillation to achieve higher exact sequence matching and dependency legality than prior external-graph methods.
Agent-BOM is a unified hierarchical attributed directed graph that models static capability bases and dynamic semantic states of LLM agents for path-level security auditing and risk assessment.
AutoSurrogate is a multi-agent LLM framework that autonomously constructs, tunes, and validates deep learning surrogates for subsurface flow from natural language, outperforming expert baselines on a 3D carbon storage task.
The paper introduces the Agentic Risk Standard (ARS) as a payment settlement framework that delivers predefined compensation for AI agent execution failures, misalignment, or unintended outcomes.
GrantBox evaluates LLM agents using real-world tools and finds they remain vulnerable to sophisticated prompt injection attacks with an 84.80% average success rate.
DoubleAgents shows that a distributed-cognition design with coordination agent, dashboard, and policy module increases user comfort and reliance on AI agents for coordination tasks over time.
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
BlindGuard introduces an unsupervised hierarchical agent encoder plus corruption-guided contrastive detector that identifies malicious agents in LLM-based multi-agent systems without any attack labels or prior knowledge of malicious behaviors.
DeepResearch Bench supplies 100 expert-crafted PhD-level tasks and two human-aligned evaluation frameworks to measure deep research agents on report quality and citation accuracy.
EmbodiedClaw automates embodied AI development workflows through conversation, reducing manual effort and improving consistency and reproducibility.
AgentOpt introduces a framework-agnostic package that uses algorithms like UCB-E to find cost-effective model assignments in multi-step LLM agent pipelines, cutting evaluation budgets by 62-76% while maintaining near-optimal accuracy on benchmarks.
Small language models are sufficiently capable, more suitable, and far more economical than large models for the repetitive tasks that dominate agentic AI systems.
Magentic-One is a modular multi-agent system that matches state-of-the-art performance on GAIA, AssistantBench, and WebArena using an orchestrator-led team of specialized agents.
HiLSVA introduces a plan-first multi-agent LLM system for scientific visualization that incorporates explicit human oversight, stepwise provenance, and learn-at-test-time adaptation, evaluated via case studies and a 12-participant user study.
Proposes and tests a constitutive definition of 'agent harness' via conceptual analysis of literature and six real systems.
Proposes guidance for responsible AI use in scientific software development under NQA-1 standards, illustrated with TMAP8 V&V cases to ensure accountability and auditability.
Agentic AI needs social theory as structural priors in the MASS framework to model emergent dynamics from multi-agent interactions.
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.