arXiv||1 min read
Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation
Focuses on Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation.
Topic archive
Agents AI news
Tool use, planning, orchestration, and agent workflows. This page collects the latest briefings that match the topic so readers can follow one area without scanning the full feed.
Indexed briefings
973
Latest source-linked updates, ordered newest first.
Latest
Recent briefings
arXiv||1 min read
CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?
Focuses on CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses?.
arXiv||1 min read
The Rise of Verbal Reinforcement Learning
Focuses on The Rise of Verbal Reinforcement Learning.
arXiv||1 min read
Mechanism Design for Alignment and Control
Focuses on Mechanism Design for Alignment and Control.
arXiv||1 min read
Designing Proactive Thought Partners for Writing
Focuses on Designing Proactive Thought Partners for Writing.
arXiv||1 min read
Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers
Focuses on Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers.
arXiv||1 min read
Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories
Focuses on Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories.
arXiv||1 min read
NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games
Focuses on NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games.
arXiv||1 min read
EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation
Focuses on EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation.
OpenAI||1 min read
How AI-native companies turn workflows into operating capability
Basis, Clay, and Exa Labs use AI agents to improve onboarding, account management, and developer integrations.
arXiv||1 min read
When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation
Focuses on When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation.
arXiv||1 min read
DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk Screening
Focuses on DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk Screening.
arXiv||1 min read
GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions
Focuses on GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions.
arXiv||1 min read
Aspire: Can Models Self-Evolve from Vague Goals?
Focuses on Aspire: Can Models Self-Evolve from Vague Goals?.
arXiv||1 min read
Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents
Focuses on Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents.
arXiv||1 min read
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement
Focuses on Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement.
arXiv||1 min read
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Focuses on S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?.
arXiv||1 min read
Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers
Focuses on Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers.
arXiv||1 min read
Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data
Focuses on Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data.
arXiv||1 min read
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Focuses on HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?.
arXiv||1 min read
Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization
Focuses on Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization.
arXiv||1 min read
TRIAGE: Three-level Routing and Intelligent Agent Guidance for Efficient Execution
Focuses on TRIAGE: Three-level Routing and Intelligent Agent Guidance for Efficient Execution.
arXiv||1 min read
Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents
Focuses on Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents.
arXiv||1 min read
Provably Safe Sim-to-Real Transfer
Focuses on Provably Safe Sim-to-Real Transfer.
arXiv||1 min read
Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence
Focuses on Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence.
arXiv||1 min read
EdiTikZ: Scientific Figure Editing from Revision Trajectories
Focuses on EdiTikZ: Scientific Figure Editing from Revision Trajectories.
arXiv||1 min read
Measure Before You Manage: Evaluating Agent Working Memory in Coding Agents
Focuses on Measure Before You Manage: Evaluating Agent Working Memory in Coding Agents.
arXiv||1 min read
Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching
Focuses on Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching.
arXiv||1 min read
Logos: An Agent Harness on a Cross-Process Bus
Focuses on Logos: An Agent Harness on a Cross-Process Bus.
arXiv||1 min read
Autonomous robotic bridging using distributed swarm control without inter-agent communication
Focuses on Autonomous robotic bridging using distributed swarm control without inter-agent communication.
arXiv||1 min read
InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations
Focuses on InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations.
arXiv||1 min read
On the Maintenance and Co-evolution of Agent Plugins: An Empirical Study of Claude Code Plugin Marketplaces
Focuses on On the Maintenance and Co-evolution of Agent Plugins: An Empirical Study of Claude Code Plugin Marketplaces.
arXiv||1 min read
Analytic Dynamics: Learning Physics-Grounded Representation for Fast Intrinsic Dynamics Inference from Monocular Videos
Focuses on Analytic Dynamics: Learning Physics-Grounded Representation for Fast Intrinsic Dynamics Inference from Monocular Videos.
arXiv||1 min read
EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems
Focuses on EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems.
arXiv||1 min read
MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents
Focuses on MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents.
arXiv||1 min read
LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting
Focuses on LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting.