pith. sign in

Alas: Autonomous learning agent for self-updating language models

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 2

citation-polarity summary

fields

cs.AI 1 cs.LG 1

years

2026 1 2025 1

roles

background 2

polarities

background 2

representative citing papers

Autolearn: Learn by Surprise, Commit by Proof

cs.LG · 2026-04-02 · unverdicted · novelty 6.0

Autolearn uses high-loss passages and self-generated Q&A training to drive the perturbation gap below baseline, improving novel fact acquisition while suppressing memorization in language models.

citing papers explorer

Showing 2 of 2 citing papers.

  • Autolearn: Learn by Surprise, Commit by Proof cs.LG · 2026-04-02 · unverdicted · none · ref 25

    Autolearn uses high-loss passages and self-generated Q&A training to drive the perturbation gap below baseline, improving novel fact acquisition while suppressing memorization in language models.

  • The Landscape of Agentic Reinforcement Learning for LLMs: A Survey cs.AI · 2025-09-02 · accept · none · ref 176

    Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.