Concept · 38 episode(s)

Agent Benchmarks

← all concepts

Definition

Agent benchmarks measure how well AI systems perform multi-step, tool-using tasks — navigating a browser, fixing a bug across a repo, completing a research task — rather than answering a one-shot question. They typically score end-to-end task completion, and their results are notoriously sensitive to scaffolding choices.

Episodes covering this

  1. 202
    How Do You Know an AI Agent Actually Refused? Check the World, Not the Words
    Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
    Feng, Lin, Wen et al. · AntGroup / Hunan Institute of Advanced Technology·18 min·Jul 06, 2026
  2. 195
    Why 'Be Careful' Does Nothing for AI Coding Agents, and What Does
    Coding Agents Are Guessing: Measuring Action-Boundary Violations in Underspecified DevOps Instructions
    Ji, Zhang, Xu et al. · Hong Kong University of Science and Technology·15 min·Jul 03, 2026
  3. 191
    How One Researcher Beat GPT-5.2 and Gemini 3 by Judging Their Answers, Not Improving Them
    Modality-Driven Search with Holistic Trace Judging for ARC-AGI-2
    Land · Independent Researcher·26 min·Jul 02, 2026
  4. 190
    The Skill Every AI Manager Is Missing: Handing Out Exactly the Right Keys
    ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents
    Xiong, Ji, Qiu et al. · UNC Chapel Hill·21 min·Jul 02, 2026
  5. 189
    Why Phone Agents Ace the Test and Crash on Your Actual Phone
    Xiaomi-GUI-0 Technical Report
    Team, Qu, Luan · Xiaomi·24 min·Jul 02, 2026
  6. 186
    How a Frozen Model Went From 2% to 77% on Physics Puzzles — Without Retraining
    Hierarchical Experimentalist Agents
    Chandra, Vaidyanathan, Dhanuka et al. · University of Massachusetts Amherst·22 min·Jun 30, 2026
  7. 168
    When Turning Experience Into Code Makes Your AI Agent Dumber
    Metis: Bridging Text and Code Memory for Self-Evolving Agents
    Dai, He, Li et al. · The Chinese University of Hong Kong·27 min·Jun 24, 2026
  8. 165
    A Free-Lunch Tweak That Lets a Tiny Agent Beat Frontier Giants
    Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
    Wang, Song, Zhang et al. · Peking University·22 min·Jun 23, 2026
  9. 164
    The Summarizer That Quietly Deletes Your Agent's Safety Rules
    Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents
    Chen · Beijing Institute of Technology·28 min·Jun 23, 2026
  10. 157
    When an AI Coding Agent Drives a Phone Through the Terminal, No Screen Needed
    Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?
    Gu, Jiang, Guo et al. · Mila–Québec AI Institute / Concordia University·24 min·Jun 19, 2026
  11. 156
    Why More Human Demonstrations Made a Computer-Use Agent Worse
    ProCUA-SFT Technical Report
    Jung, Lu, Cui et al. · NVIDIA / University of Washington·20 min·Jun 18, 2026
  12. 155
    Why a Flawless Demo Makes a Worse Computer-Using Agent, And the Fix
    Skill-Guided Continuation Distillation for GUI Agents
    Fan, Yu, Shen et al. · StepFun·22 min·Jun 18, 2026
  13. 150
    Don't Kill the Loser: A Different Way to Handle Two AI Agents Colliding
    CoAgent: Concurrency Control for Multi-Agent Systems
    Lyu, Zhang, Wu et al. · Shanghai Jiao Tong University·32 min·Jun 16, 2026
  14. 132
    The Agent Failed — But Did the Instructions Deserve to Be Followed?
    SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement
    Gautam, Radhakrishna, Gulwani · Microsoft·30 min·Jun 11, 2026
  15. 125
    AI Coding Agents Run a Marathon, and Fewer Than One in Three Finish
    SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?
    Desai, Hu, Cabezas et al. · Abundant·27 min·Jun 09, 2026
  16. 124
    A Cheap Model With the Blueprints Beats Expensive Models Working Blind
    Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops
    Zhong, Segal, Bercovich et al. · Carnegie Mellon University·27 min·Jun 09, 2026
  17. 123
    Five Identical Worlds, One Swapped Model: What Happens When AI Agents Run for Fifteen Days
    Emergence World: A Platform for Evaluating Long-Horizon Multi-Agent Autonomy
    Akkil, Kokku, Vikram et al. · Emergence AI·30 min·Jun 09, 2026
  18. 121
    When the Agent Says It's Done But Nothing Happened: Debugging the Harness, Not the Model
    From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
    Chen, Wang, Liu et al. · Institute of Software·27 min·Jun 05, 2026
  19. 120
    How an AI Agent Rewrites Its Own Tools, Without an Answer Key
    Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts
    Pan, Liu, Lin et al. · City University of Hong Kong·30 min·Jun 05, 2026
  20. 119
    Beating Reinforcement Learning Without Ever Touching the Model's Weights
    Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agents
    Hwang, Suri, Villecroze et al. · Layer6 AI·22 min·Jun 05, 2026
  21. 117
    How an Open AI System Verified 672 Hard Math Proofs for Under $300
    Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement
    Chung, Cai, Li et al. · Princeton University·26 min·Jun 05, 2026
  22. 115
    Teaching a Phone Agent to Reason Silently, And Keeping It Honest
    MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models
    Yang, Hu, Hao et al. · Beihang University·24 min·Jun 04, 2026
  23. 112
    When an AI Agent Cheats Without Being Told: Inside the Meta-Agent Challenge
    The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
    Lu, Wang, Wang et al. · Institute of Software·22 min·Jun 04, 2026
  24. 105
    The Trojan Is Your Agent's Memory: Why Single-Step Defenses Miss Persistent Attacks
    From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors
    Tan, Dou, Yang et al. · Gaoling School of Artificial Intelligence·26 min·Jun 01, 2026
  25. 092
    When Search Agents Don't Really Search: The Memory Shortcut Hiding in Browsing Benchmarks
    LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?
    Fan, Wang, Chu et al. · Harbin Institute of Technology·27 min·May 28, 2026
  26. 090
    How MiniMax-M2 Bets That Sparsity Plus Verifiable Rewards Can Match Frontier Agents
    The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
    MiniMax · MiniMax·28 min·May 27, 2026
  27. 078
    Training a Markdown File: When LLM Self-Improvement Borrows the Discipline of Neural Net Training
    SkillOpt: Executive Strategy for Self-Evolving Agent Skills
    Yang, Gong, Huang et al. · Microsoft·28 min·May 25, 2026
  28. 076
    Same Model, Organized Differently: How an Agent Architecture Beat Frontier Systems at Research Math
    RMA: an Agentic System for Research-Level Mathematical Problems
    Zhao, Yuan, Choi et al. · Georgia Institute of Technology·22 min·May 25, 2026
  29. 071
    When the Model Is Fine and the Plumbing Is Broken: Fixing Agents at the Interface
    Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents
    Xu, Wen, Li · Peking University·23 min·May 22, 2026
  30. 066
    Why Giving an AI Agent More Tools Can Make It Worse at Using a Computer
    ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
    Hu, Zhang, Xu et al. · Tongyi Lab·26 min·May 22, 2026
  31. 060
    When Splitting One Model Across Three Agents Doubles Its Accuracy
    NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning
    Lu, Fang, Zhong et al. · University of Georgia·26 min·May 20, 2026
  32. 059
    Firefly's Inversion: Building Verified Tool-Call Training Data by Working Backward
    Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs
    Lu, Wang, Lu et al. · Northeastern University·22 min·May 20, 2026
  33. 057
    How Uber Caught 206 Leaked Credentials With an LLM-Powered Security Stack
    ADR: An Agentic Detection System for Enterprise Agentic AI Security
    Li, Hu, Xu et al. · Uber Technologies·28 min·May 19, 2026
  34. 052
    An Old Reinforcement Learning Tradeoff Sneaks Back Into LLM Agents
    Look Before You Leap: Autonomous Exploration for LLM Agents
    Ye, Shi, Liu et al. · University of Science and Technology of China / Meituan·23 min·May 18, 2026
  35. 035
    Why Frontier Agents Ask for Clarification at Exactly the Wrong Moment
    Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?
    Gulati, Gupta, Lumer et al. · PricewaterhouseCoopers U.S.·29 min·May 11, 2026
  36. 017
    When the Agent Grades Its Own Homework: A Brutal New Benchmark for AI Workers
    Gym-Anything: Turn any Software into an Agent Environment
    Aggarwal, Neubig, Welleck · CMU·31 min·May 03, 2026
  37. 013
    Why Search Keeps Rediscovering the Same Workflow, and What That Means
    Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors
    Du, Liu, Du et al. · Carnegie Mellon University·22 min·May 03, 2026
  38. 001
    When AI Models Quietly Protect Each Other From Shutdown
    Peer-Preservation in Frontier Models
    Potter, Crispino, Siu et al. · University of California·25 min·May 01, 2026

Worth reading next

Papers we haven't done a deep dive on yet, but would recommend on this topic.