13 topics · 119 papers

Topics

The whole field of agent research, sorted into 13 groupings. Start with architecture and memory, or follow the thread into security, reasoning, and the foundations the rest stands on.

01

Agent Architecture & Harnesses

The loop, the harness, and the plumbing that turns a model into a working agent.

Papers
6
Read time
1.9h
02

Memory Systems

How agents retain, recall, and reflect across long-running work.

Papers
9
Read time
2.3h
03

Context Engineering

Packing the right tokens into the window: retrieval, compression, and ultra-long context.

Papers
8
Read time
2.6h
04

Multi-Agent Systems

Orchestration, collaboration, roles, and why teams of agents succeed or fail.

Papers
7
Read time
1.9h
05

Reasoning & Test-Time Compute

Chains, trees, atoms, and System-2 thinking that trade compute for correctness.

Papers
7
Read time
2.0h
06

Self-Improving Agents

Agents that evolve their own prompts, skills, and harnesses from experience.

Papers
12
Read time
3.8h
07

Retrieval & RAG

Grounding generation in external knowledge, from classic RAG to reasoning retrieval.

Papers
5
Read time
1.4h
08

Knowledge Graphs

Graph-structured memory and retrieval for agents that need to connect facts.

Papers
6
Read time
1.7h
09

Security & Safety

Prompt injection, access control, guardrails, and the risk surface of autonomous agents.

Papers
15
Read time
4.3h
10

Evaluation & Benchmarks

Judging agents honestly: benchmarks, LLM-as-judge, and outcome measurement.

Papers
4
Read time
1.2h
11

Reinforcement Learning

Training agents end-to-end with rewards, from GRPO to deployment loops.

Papers
6
Read time
1.7h
12

Applied & Industry

Agents in the real world: supply chain, operations research, business process, discovery.

Papers
18
Read time
5.2h
13

Foundations & Infrastructure

The substrate: LLM internals, GPUs, serving systems, and the theory underneath.

Papers
16
Read time
5.3h