← All concepts

continual learning

Continual learning is about training a model on a sequence of tasks without forgetting earlier ones. Imagine teaching a robot new skills while it keeps old ones, or updating a deepfake detector as new fakes appear. The challenge is "catastrophic forgetting": changes for new tasks overwrite old knowledge. Methods often replay past data, freeze parts of the network, or use prompts, but each has trade-offs.

The papers show a common thread: no single approach solves all continual learning problems. Off-policy reinforcement learning with distillation preserves robot skills; neuroevolution finds wider solutions that retain stability; prompt banks and filter-level updates avoid touching the backbone. But self-evolving agents and fairness-aware detectors reveal gaps: plasticity often hurts stability, and accuracy alone misses societal costs. The field is moving toward modular, parameter-efficient strategies that trade off memory, computation, and forgetting.

Papers
72
Released code
2
First seen
Sept 2026
Latest
Nov 2026

72 papers in the last two months, against 0 in the two before.

Start here

Three papers to read first, in the order they came out
  1. 1Self-evolving agents trade plasticity for stability in continual learning streams.

    Self-evolving LLM agents trade plasticity for stability: self-modification interferes across tasks, and memory retrieval causes collisions, so they are not complete continual learners.

    Oct 2026
  2. 2AI agents finish fewer than a quarter of five-stage professional tasks

    On CLE, feedback and revision improve LLM agent completion by a median of 5.3 points, with the best system clearing only 47.7% of levels.

    Oct 2026
  3. 3Two-memory approach lets AI agents learn new tasks without forgetting old ones

    Separating value functions into permanent parametric and transient non-parametric features balances stability and plasticity in continual reinforcement learning.

    Nov 2026

Who is working on it

Amazon 4Tsinghua University 3NVIDIA 3Mila 2Mila – Quebec AI Institute 2The Hong Kong Polytechnic University 2

The papers

Most central to this idea first, not most recent.

Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.