Agent

What it is

The system implements a loop where the LLM evaluates the current state, selects a tool from a defined registry, and executes the call. It interprets the tool output to determine the next step or whether the final goal is met. These loops typically involve 3 to 10 sequential model calls per user request, significantly increasing the latency and cost per transaction compared to a single-shot prompt. Managing the persistent state across these steps is the primary architectural requirement for agentic systems.

Why it matters

Moving from static prompts to agents shifts your architecture from request-response to stateful long-running workflows. You must manage complex error handling, infinite loop detection, and cost spikes caused by excessive model calls. If you ignore these dynamics, you will likely hit API rate limits and experience silent failures where the agent gets stuck in a recursive loop without the user knowing.

In practice

In production, you monitor the agent by tracking the number of steps per trace and the cumulative token usage for each request. You will frequently tune the system prompt and the tool descriptions to minimize unnecessary calls, often using observability tools to debug the reasoning chain within the agent's loop.

The tradeoff

The main tradeoff is that increasing agent autonomy improves performance on complex tasks but drastically reduces predictability and increases the surface area for hallucinations.

Where it appears

Research summaries that use Agent, each linked to its source paper.

• Building Intelligent Basketball AI Agents
  Towards Comprehensive Basketball Understanding

  The researchers introduced a multimodal benchmark and an agentic framework that outperforms commercial models in complex basketball reasoning tasks.

• Securing Autonomous AI Agents with ClawSentry
  ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents

  ClawSentry provides a modular, multi-tier security framework that uses an abstraction protocol to protect autonomous LLM agents against progressive execution threats.

• Benchmarking Agent Harness Safety Lifecycles
  HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety

  HarnessRisk provides a lifecycle based framework for evaluating security vulnerabilities across six distinct operational phases in agentic systems.

• Building Realistic Mental Health Simulation Agents
  PatientAct: Theory-Grounded Mental Health Client Simulation

  The paper introduces PatientAct, a framework designed to simulate mental health clients using clinical theory to improve realism in LLM-based agent interactions.

• Autonomous Software Evolution via Recursive Worlds
  Persistent Recursive Worlds Enable Autonomous Software Evolution

  The study demonstrates a framework called Genesis that enables autonomous agents to build complex software by using persistent recursive states and iterative validation to evolve codebases from empty repositories.

• Benchmarking AI Agents on Code Refactoring
  SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

  The paper introduces SWE-Bench ProMax, a new, expert-curated benchmark designed to evaluate AI coding agents on complex, large-scale, multilingual refactoring tasks.

• Improving AI Terminal Task Construction
  CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks

  CalibForge uses automated adversarial feedback from software solvers to ensure that training tasks for LLM agents are neither too simple nor impossible to solve.

• Selecting Better Training Data for Agents
  SWE-Prime: Fewer Trajectories, Better Performance

  The researchers introduced SWE-Prime, a method that selects a small, high-quality subset of training trajectories to improve software engineering agent performance.

• Building Persistent Knowledge for AI Agents
  WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

  WikiSkill improves AI agent performance by consolidating execution traces into a structured, persistent wiki that informs future skill development.

• Improving AI Agent Execution Through Live Steering
  PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents

  The PILOT harness allows AI agents to improve their performance in real time by employing a supervisor that provides live feedback and distills successful strategies during task execution.

• Testing AI Navigation in Virtual Cities
  UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City

  The paper introduces UrbanGround, a sandbox environment using real-world 3D mapping data to evaluate how well MLLM agents navigate complex urban settings.

• Standardizing Data Generation for AI Agents
  What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents

  The ACE framework establishes a formal structure for evaluating and improving the data generated to train autonomous AI agents.

• Improving Reliability in Autonomous Agent Systems
  Agent Mesh: Reliability Primitives for Non-Idempotent Agent Delegation - Identity Adequacy and Evidence Adequacy

  The paper introduces Agent Mesh to address unique reliability challenges in agentic software development by defining new primitives to manage non-idempotent tool delegations.

• Decoupling Persona and Execution for Agents
  Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Audit

  The paper introduces a dual-domain architectural pattern that separates an AI agent's persona from its execution logic to improve governance and auditability in regulated environments.

• Debugging LLM Multi-Agent System Failures
  Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems

  The authors introduce SymTrace, a framework that improves the reliability of debugging complex multi-agent systems by using controlled intervention anchors to replicate and repair execution failures.

• Agentic Framework for Traffic Anomaly Understanding
  TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding

  TAU-Agent is an agentic framework designed to improve traffic anomaly detection by using retrieval-augmented generation to integrate video descriptions and object trajectories.

• Automated Video Editing Through Verifier-Grounded Planning
  Plans You Can Check: Verifier-Grounded Learning of an Open-Weight Planner for Executable Video-Editing

  The authors introduce a framework for video-editing agents to generate and verify executable edit plans using a self-improving training loop.

• A Framework for Dynamic Software Composition
  A Programming Paradigm for Spatiotemporal Composability

  The authors introduce a framework called Cordis that uses a context paradigm to enable reliable dynamic composition of software components.

• Using Coding Agents as World Brains
  Code World Model: Coding Agent as World Brain

  The paper introduces a framework where a coding agent generates deterministic code to manage world state, which then guides a video model to maintain visual consistency in simulated environments.

• Improving AI Web Page Generation with Rubrics
  Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation

  RubSE improves AI code generation for web pages by using structured visual rubrics to guide iterative, self-evolving refinements.

• Evaluating Android Agent Robustness to Anomalies
  Are Android GUI Agents Robust Against Runtime Anomalies? AnTrap: Evaluating Agents in Dynamic Adversarial Environments

  The paper introduces AnTrap, a benchmark that tests how Android GUI agents handle dynamic environmental anomalies by injecting perturbations into 236 tasks.

• Evaluating Autonomous Scientific Agent Performance
  FrontierChallenge: Evaluating Scientific Workflow Completion

  The paper introduces FrontierChallenge, a benchmark for evaluating how well AI agents complete end-to-end scientific workflows.

• Real-Time Streaming Memory for AI Agents
  VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction

  VoiceMem is a dual-brain architecture designed to provide accurate, low-latency memory retrieval for speech-based conversational agents.

• Agentic Multimodal Instruction Data Synthesis
  VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following

  The researchers developed an agentic, iterative framework called VISA to generate high-quality training data for multimodal models by using feedback-driven loops instead of static one-pass pipelines.

• Improving AI Agent Planning for Development
  TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development

  The paper introduces a planning framework for AI coding agents that aligns their development processes with human practices to improve task performance.

• Dynamic Optimization of AI Agent Harnesses
  JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

  JIT-Agent improves agent performance by dynamically generating and evolving task-specific control structures just in time to meet individual task demands.

• Auditing Logic in LLM Data Agents
  Trace Integrity for LLM Data Agents: A Vision for Auditable Structured Reasoning in Real-World Systems

  The paper introduces trace integrity metrics to detect silent failures where LLM data agents produce correct answers through invalid logical steps.

• Dynamic Routing for Efficient LLM Agents
  ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs

  ProgRouter optimizes multi-agent workflows by dynamically selecting models based on progress and cost to maximize task completion rates within defined energy budgets.

• Building Verifiable Skills for Reinforcement Learning
  SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agents

  SkillForge introduces a system that distills and verifies reusable skills for agents, significantly improving performance on complex tasks.

• Benchmarking Reliability in Scientific AI Agents
  EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural Hazards

  The paper introduces EarthVerse, a benchmark designed to evaluate how accurately scientific agents perform end to end investigations involving Earth systems and natural hazards.

• Optimizing LLM Agents for Competitive Programming
  MARS: Multi-Specialist LLM Relay System for Competitive Programming

  The Multi-Specialist LLM Relay System improves coding agent performance by using specialized agents and a staged pipeline to solve complex programming tasks.

• Optimizing Agentic Search Under Budget Constraints
  Exploit More, Explore Smarter for Budget-Constrained Agentic Search

  ExTS improves search efficiency by adapting tree search strategies based on diagnostic pilot runs that characterize the search landscape.

• Linking Code and Prose for Coding Agents
  A Literate Programming Environment for Human and Machine Agents

  The paper introduces notlob, a system that maintains a graph of prose and code to improve how coding agents navigate and manage development context.

• Improving Agent Efficiency with Stream Aligned Optimization
  SPO++: Stream-Aligned Policy Optimization for Asynchronous Agentic RL

  SPO++ is a refined policy optimization framework that increases online learning efficiency for language agents by aligning data tracking with event timing.

• Improving Multi-Turn AI Agent Credit Assignment
  IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents

  The paper introduces IAPO, a method that improves agent training by redistributing reward credit based on how agent actions influence one another within multi-turn service workflows.

• Autonomous Multi-Agent Mathematical Discovery
  Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment

  Researchers built an open-world multi-agent system that autonomously explores complex mathematical problems by having independent agents read, write, and verify findings in a shared research environment.

• Preserving Critical Constraints in LLM Workflows
  When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows

  The paper demonstrates that standard LLM agent handoff processes often cause binding constraints to lose their functional power, and identifies methods to restore this operational state.

• Building Autonomous Agents for Molecular Discovery
  Molecular LLM Agents: From Architectural Design to Scientific Autonomy

  The paper introduces a framework and an autonomy classification system for deploying Large Language Model agents in scientific molecular discovery workflows.

• Predicting Agent Behavior with Automata
  Automata from Agent Traces: Failure and Next-Step Prediction

  The paper introduces a method that models agent behavior as finite state machines to improve next-step prediction and detect system failures.

• Improving AI Memory Evaluation in Conversation
  MemUse: Moving Memory Evaluation from Direct QA to Natural Integration in Long-Term Human-AI Conversation

  The paper introduces MemUse, a benchmark for evaluating how well conversational AI integrates long-term memory into natural dialogue, revealing a significant disconnect between standard fact-checking performance and actual conversational utility.

• Agent-Driven Framework for Simulating LLM Serving
  Simthesizer: An Agent-Driven Simulation Framework for LLM Serving Systems

  Simthesizer utilizes a coding agent to automatically extend simulators for complex LLM serving systems, achieving higher throughput accuracy than existing approaches.

• Improving Agent Search with Persistent Navigation
  Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNav

  AtlasNav introduces a persistent navigation layer for AI agents to prevent evidence loss during large-scale document corpus interactions.

• Structuring Agentic Research with Evidence Graphs
  Structurally-bounded Agentic Graph Exploration for Evidence-Grounded Scholarly DeepSearch

  The paper introduces Crase, an agentic system that bounds research discovery within a citation graph to improve evidence grounding and search accuracy.

• Recursive Self-Improving AI Agent Architecture
  Meta$^n$: Recursive Self-Improvement through Emergent Depth

  The Meta n system introduces a recursive architecture that enables agents to iteratively improve their own problem-solving logic and code libraries.

• Improving Enterprise Agent Performance with Evolving Harnesses
  StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments

  StarHarness evolves environment-specific agent harnesses to improve task success rates and lower inference costs in enterprise environments.

• Scaling Web Agents With Browser Sandboxes
  BrowserForge: Scaling Web Episode via Parallel Browser Sandboxes

  Researchers built a large-scale web navigation dataset by orchestrating parallel browser sandboxes to generate diverse, high-quality interaction trajectories.

• Building Safer LLM Agent Tool Usage
  StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing

  StepGuard provides a 4B guard model that validates agent tool actions before execution to reduce unsafe behaviors while maintaining performance.

• Improving AI Search Agents With Co-evolving Feedback
  CAFE: Self-Improving Search Agents Need Co-Evolving Feedback

  The paper introduces CAFE, a system that improves search agent performance and reduces hallucinations by alternatingly updating the agent and its critic through co-evolving feedback.

• Improving Multi-Turn AI Agent Tool Use
  From State to Action: OODA-Tool for Reliable Multi-Turn Tool Use

  The OODA-Tool method improves reliability in complex multi-turn tool interactions by decoupling state management from the process of executing actions.

• Jointly Training AI to Create and Use Tools
  Joint Optimization of Tool Creation and Use for Large Language Model Agents

  The SMITH framework uses reinforcement learning to train a single language model to both synthesize reusable Python tools and apply them effectively to solve complex tasks.

• Optimizing Model Handoffs in Coding Agents
  The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents

  The paper investigates the efficiency and accuracy trade-offs when transitioning tasks between low-cost and high-cost language models in agentic coding workflows.

• Benchmarking Resource Aware LLM Tool Agents
  PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents

  The paper introduces PeakBench to evaluate how effectively AI agents manage system resources when executing parallel tool workflows.

• AI Assistance and Its Impact on Skill Development
  How AI Assistance Affects Human Skill Development: A Study of Learning with Logic Puzzles

  The paper investigates whether providing on-demand AI assistance for logic tasks reduces the user's ability to develop independent problem-solving skills.

• Measuring Model Performance on Scientific Requests
  K-Bench: measuring model performance on real scientific agent requests

  The paper introduces K-Bench 01 to evaluate how frontier models perform on real-world scientific agent requests sampled from live user traffic.

• Efficient Semantic Navigation for Autonomous Robots
  OptiSight: Bridging Semantic Reasoning and Geometric Control for Embodied Navigation

  OptiSight combines semantic object identification with geometric control to enable efficient robot navigation while minimizing reliance on high-frequency language model inference.

• Checking LLM Generated Trading Strategy Reliability
  FIDES: A Concordance Protocol for LLM-Generated Trading Strategies

  The paper introduces a protocol to verify if trading strategies generated by large language models align with their actual performance, finding that most claimed advantages fail to materialize.

• Automating Agent Skill Creation From Data
  SkillAlchemy: Open-World Agent Skill Creation

  SkillAlchemy introduces a systematic approach to converting open world information into reliable, reusable procedural skills for software agents.

• Scaling Cyber Security Skills With AI
  CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild

  The researchers developed CyberFactory, a framework that leverages existing vulnerability data to train an AI model, OpenAegis, to improve security analysis performance.

• Building Reliable Autonomous Research Agents
  AutoResearch: Insight In, Hallucination Out

  AutoResearch is an autonomous system that uses multi-model cross-review to improve the reliability of research idea generation and experimental validation.

• How Multi-Agent Communication Limits Solution Diversity
  The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams

  The paper demonstrates that full-solution interaction between agents can cause proposals to converge too quickly, erasing useful diversity and reducing performance on specific optimization tasks.