Introduction
Artificial Intelligence is moving beyond simple rule-based systems towards agents that can plan, reason and act autonomously. Present day AI systems research are focused on building artificial agents capable of performing variety of real world tasks.
In this blog, I will share my findings from two very recent Artificial Intelligence research papers and relate them to concepts that would be studied in Artificial Intelligence course: intelligent agents, search and heuristics.
The Artificial Intelligence research papers used are:
"The Rise of Agentic AI: A Review of Definitions, Frameworks, and Challenges (2025)"
"Research on the A* Algorithm Based on Adaptive Weights (2025)"
The first paper discuss agentic artificial intelligence, a newer approach to AI where agents is able to perform tasks autonomously after independent planning.
The second paper discuss improvements to the A* search algorithm, one of the most commonly utilized algorithms for pathfinding and optimization task in Artificial Intelligence.
Both research papers highlights the continuing advancement of artificial intelligence from foundational principles that we learn in artificial intelligence courses and builds on them in ways that allow more efficient systems to perform complex real world tasks.
What is Agentic AI?
The first research paper focus on agentic AI. This is system of artificial intelligence that is autonomous, able to perform a variety of different tasks and have the ability to plan.
Whereas previous AI agents could receive input and respond or predict information, agentic AI have the ability to respond and then performs several different actions.
Intelligent agents within the field of AI is typically described as agents which can:
perceive their environment
reason with information
act to achieve certain goals
Agentic AI further define this as agents which can perform multiple steps of planning. For example, an agentic system could:
search for information
evaluate various sources
use the information to create appropriate response
This would shows a significant advancement from simple AI, which may just receive information and generate a simple answer, to an autonomous problem solving system.
Frameworks Used in Agentic AI
Several frameworks have been developed in Agentic AI for creating agentic systems. The most important types have been discussed in the paper and can be briefly summarize below:
- Planning-Based Agents
These agents is the most direct implementation of what we learn in artificial intelligence courses about goal based agents. They breaks tasks into smaller goals which is solved sequentially. As an example, an agentic system trying to compile a report would have goals of information retrieval, analysis, synthesis, compilation, writing and presentation.
- Tool-Using Agents
Agentic systems is often designed with external tools in mind, such as Application Programming Interfaces (APIs), search engines and other specialized tools for complex problems. This can expands the capabilities of an agentic AI system far beyond what its internal parameters or learning would provides.
- Reasoning & Action Loop
This refers to an iterative process of decision making for an agentic AI system. At each step, the system analyze the state of the world it perceives, decide on course of action, then execute that action. The results is then analyzed and feed back into the cycle in order to adapt to the evolving world and task objectives.
Challenges with Agentic AI
As has been indicated throughout, Agentic AI represent an enormous leap in the field of Artificial Intelligence. However, there is some obvious challenges presented in the research paper.
Reliability
If an agent make the wrong assumptions about what actions need to be taken or what data is needed, the agentic system could produces unreliable outputs.
Safety
Given that the agentic AI can automatically executes actions, there needs to be some safety protocol or control mechanism to ensure that it do not do something damaging.
Long-Term Planning
While simple actions are already an advancement for AI agents, carrying out long term sequences of actions and maintaining context are area which needs a lot more research.
The challenges are presented clearly, demonstrating the extent to which agentic AI is still a new field which require research to develop to its full potential.
Research on Adaptive A*
The second paper I reviewed concern advancements to one of the most well known and extensively utilized search algorithms in artificial intelligence, the A* search algorithm. The research have focused on improving the performance and efficiency of A* with adaptive weightings.
A* is used to solve optimization problems where the path have to go from A to B and is most commonly seen in games, navigation systems, logistics, robot navigation and much more.
The A* algorithm finds the path by using the function f(n)=g(n)+h(n), where g(n) is the actual cost from the start to node n and h(n) is the heuristic estimate from the node to the goal node.
The A* algorithm prioritize searching nodes with the lowest f(n) value, resulting in optimal search and efficiency provided the heuristic is good enough.
In the paper I researched, they implemented an adaptation to the A* search algorithm using a varying weight. Traditionally, a heuristic have a weight of one and does not change. This proposed algorithm utilize a variable heuristic where the weight assigned by the algorithm to the heuristic can be modified during the search in order to balance the search between finding optimal and feasible paths. They discovered that the algorithm would favors heuristic results at the beginning of the search (giving it more room to explore), and when approaching the goal it would favor the actual path to the goal in order to try to find solution quickly and with minimal searching.
Benefits of the Adaptive Approach to A*:
Faster path identification
A reduction in nodes searched
Improved efficiency
Conclusion
The papers have offered two differing insights into the field of AI and artificial agents, but both shows the progression that we are making. Agentic AI shows step towards machines which have greater independent decision making and can carry out tasks with much less interaction from users, whereas the improved A* search algorithm simply increase the speed of AI agents which utilize pathfinding. In essence, both papers is proving that the AI we have today is ever getting more capable and adaptable.
YouTube Video Link
Special Mention
Raqeeb
Top comments (0)