Research desk
The papers behind how we build
An annotated reading list. Every entry is credited to its original authors, with a note on what it changes once the idea meets a real system.
All entries
1 entry
- 2026ICML 2026PublishedCurated
Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning
Group-based reinforcement learning methods credit whole trajectories by final outcome, which makes it hard to see the contribution of individual steps — including valuable steps buried inside failed trajectories. The authors propose Graph-based Group Policy Optimization (GraphGPO), which aggregates all rollout trajectories into a unified state-transition graph, estimates the distance from each state to the task goal using global information encoded in the graph, and assigns credit to each edge by how much the transition reduces that distance. They report improved training efficiency and state-of-the-art performance across a range of benchmarks.
Browse by topic
Foundations
The architectures and pre-training results everything else stands on.
3 entries
Retrieval & RAG
Grounding a model in documents you actually own.
5 entries
Reasoning
Getting a model to show its work, and checking the work.
6 entries
Agents & Tool Use
Models that call tools, hold state, and finish multi-step jobs.
8 entries
Adaptation
Changing what a model does without retraining all of it.
4 entries
Alignment
Steering outputs toward what a person would accept.
6 entries
Evaluation
How you know it works before a customer finds out it does not.
11 entries