trajectory

Definition

The full record of what an AI agent did from start to finish on a task.

A sequence of states, actions, and observations produced by an agent over the course of a task, used as the unit of training data in agentic RL.

Also called: trajectories

Mentioned in 34 episodes

1. 079
   An Old Idea From Cognitive Psychology Reshapes How We Reward Reasoning Models
2. 078
   Training a Markdown File: When LLM Self-Improvement Borrows the Discipline of Neural Net Training
3. 077
   Reading a Model's Confidence Curve to Decide When Chain-of-Thought Is Worth It
4. 073
   When Three LLMs Talk to Each Other, Their Ideas Quietly Stop Moving
5. 071
   When the Model Is Fine and the Plumbing Is Broken: Fixing Agents at the Interface
6. 069
   When Smarter Models Forecast Worse: The Hidden Failure Mode in LLM Predictions
7. 068
   The OS Trick That Makes Tree Search Practical for Coding Agents
8. 066
   Why Giving an AI Agent More Tools Can Make It Worse at Using a Computer
9. 064
   When Agent Memory Stops Being a Database and Starts Being a Skill
10. 061
    When Helpful Agents Go Sideways: A 404 Error, Campus Security, and Why Alignment Misses This
11. 059
    Firefly's Inversion: Building Verified Tool-Call Training Data by Working Backward
12. 053
    An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script
13. 052
    An Old Reinforcement Learning Tradeoff Sneaks Back Into LLM Agents
14. 051
    Why Parallel Sampling Plateaus, And What Evidence Graphs Do Instead
15. 048
    How a 30B Open Model Reached Olympiad Gold With the Right Recipe
16. 047
    When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
17. 044
    How One Sentence and a Forged History Flip the Most Aligned Models
18. 042
    An Agentic Scientific Computing System That Actually Remembers What It Learns
19. 041
    When the Iteration Teaches the Model to Skip the Iteration
20. 040
    Two Frozen Models Learn to Whisper: Coupling Through Hidden States
21. 037
    Why Hallucination Detectors Miss Stale Facts: A Geometric Story About What Models Know But Don't Say
22. 035
    Why Frontier Agents Ask for Clarification at Exactly the Wrong Moment
23. 028
    Teaching a Model to Hire Copies of Itself: Recursive Agent Optimization
24. 027
    When AI Agents Build the Serving Stack: A Bet on Bespoke Infrastructure
25. 025
    The Missing Gradient Term That Predicts Sycophancy in RLHF
26. 021
    Ten Thousand Examples Beat the Full Industrial Pipeline for Search Agents
27. 019
    When the Best Reward Model Trains the Worst Policy: Inside EvoLM
28. 017
    When the Agent Grades Its Own Homework: A Brutal New Benchmark for AI Workers
29. 013
    Why Search Keeps Rediscovering the Same Workflow, and What That Means
30. 011
    When RL Actually Teaches Agents Something New, And When It Doesn't
31. 008
    Why Long-Horizon AI Agents Get Stuck, and a Milestone-Based Fix That Helps
32. 007
    Exploration Hacking: When Models Sabotage Their Own RL Training
33. 005
    Why a Debugger Designed for Humans Is the Wrong Tool for an AI Agent
34. 002
    An AI Ran a Real Optics Lab for 21 Hours and Found a Transformer-Shaped Pattern in Light

Related concepts