Language Agents Framework

Approach embedding LLMs within architectures for memory, planning, reasoning, action-selection; route to robust agency.

Neighborhood — ranked by edge-count

paper

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Tool AI frameworkframework0.786
Bostrom's category of AIs that perform specific tasks without overarching goals.
Frameworkconcept0.763
1984 Ashton-Tate integrated system with frames, FRED language, and overlapping windows; design reference for Playground's approach.
Andreas 2022: Language models as agent modelsconcept0.761
Paper hypothesising LLMs model agent beliefs/desires/intentions with preliminary GPT-3 evidence; cited as ref 2
Language Modelsconcept0.750
Primary substrate for manifold steering experiments; demonstrates method on reasoning and in-context tasks.
Role Play Framework for Dialogue Agentsframework0.743
The primary conceptual framework proposed: understanding dialogue agent behaviour as role play of characters
Language Modelconcept0.735
Primary test domain for manifold steering, including reasoning and ICL tasks
Goal Directed Frameworkframework0.733
Genie AI frameworkframework0.730
Bostrom's category of AIs that produce desired results given commands but do not act autonomously.