REVIEW 8 cited by
AI Agents: Evolution, Architecture, and Real-World Applications
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This paper examines the evolution, architecture, and practical applications of AI agents from their early, rule-based incarnations to modern sophisticated systems that integrate large language models with dedicated modules for perception, planning, and tool use. Emphasizing both theoretical foundations and real-world deployments, the paper reviews key agent paradigms, discusses limitations of current evaluation benchmarks, and proposes a holistic evaluation framework that balances task effectiveness, efficiency, robustness, and safety. Applications across enterprise, personal assistance, and specialized domains are analyzed, with insights into future research directions for more resilient and adaptive AI agent systems.
Forward citations
Cited by 8 Pith papers
-
SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents
SciVisAgentBench provides 108 expert-crafted tasks and a mixed LLM-plus-deterministic evaluation pipeline for benchmarking AI agents that perform scientific visualization workflows.
-
PARALLEL: A Prefrontal-Aligned Reinforcement inspired Approach for Language-Model Learning under Explicit Limits
PARALLEL learns per-sample LoRA update intensity (skip/light/strong) with a budget-constrained REINFORCE controller, retaining 94–99% of full-adaptation performance at 30% update mass.
-
Agentic Services Computing
A position and survey paper that defines Agentic Services Computing, a lifecycle-based framework for engineering LLM agents as governed, first-class services.
-
Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities
A survey that groups graph-empowered AI agent research into planning, execution, memory, and multi-agent coordination, plus agents-for-graphs and applications.
-
How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests
AI coding agents mostly handle routine, well-scoped development tasks; their pull requests are merged at similar rates and have comparable or lower bug-proneness than human-written pull requests across repository lifecycles.
-
Toward Edge General Intelligence with Agentic AI and Agentification: Concepts, Technologies, and Future Directions
A survey that organizes agentic AI for 6G edge networks into four pillars, compactness, efficiency, knowledge and reasoning, and migration, and illustrates them with prior case studies.
-
BetaWeb: Towards a Blockchain-enabled Trustworthy Agentic Web
BetaWeb promises a blockchain-enabled trustworthy agentic web, but the submitted manuscript body is a different mining-robot paper, leaving the proposal without supporting evidence.
-
Towards Log Analysis with AI Agents: Cowrie Case Study
A rule-based pipeline processes 313,412 Cowrie honeypot log events into 26,368 labeled attacker sessions and reports that most are automated low-skill probes.
Discussion (0). Continue with ORCID to comment.