arXiv:2607. 07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn?
FedSEAM is a federated continual learning framework that trains large language models across multiple clients without sharing data, using sparse mixture-of-experts to adapt selected parameters on a frozen backbone. It introduces task-aware tile selection for new tasks and a subspace-based compatibility test to decide which expert tiles to reuse or replace. On the server, Subspace Expert Agreement Merging (SEAM) aligns client updates only along agreed subspaces, while additional protections mitigate routing drift and merge erasure, preserving prior knowledge during training.
arXiv:2606. 07500v1 Announce Type: cross Abstract: Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge.
HERO is a heterogeneous continual graph learning framework that preserves historical knowledge at both structural and semantic levels while adapting to new tasks. It uses DiSCo to select representative target nodes and reconstruct compact heterogeneous contexts, and applies multi-level knowledge distillation to align task-conditioned predictions with semantic responses. Experiments on four datasets with three HGNN backbones show HERO achieves best or tied-best average performance while maintaining competitive forgetting.
The paper introduces Evolving Functional REpertoires (EFRE), a method that replaces a single prompt with a dynamic set of functions to enable large language models to learn new tasks sequentially without forgetting. EFRE refines existing functions when updates are compatible and creates new ones when updates conflict, thereby mitigating catastrophic forgetting and overfitting. Experiments on a three‑task continual‑learning stream show EFRE outperforms GRPO by 7.50 percentage points and reduces performance drop on a subsequent task by only 1.56 percentage points compared to base prompt optimization.
The paper introduces Skill Schema Transport (SST), a post‑training framework that mitigates catastrophic forgetting in continual domain adaptation by translating new domain knowledge into a model’s existing skill space. SST abstracts each example type into a reusable skill schema, preserving essential operations while removing domain‑specific surface forms, thereby turning knowledge updates into procedural reuse rather than trajectory memorization. Experiments on two 3B instruction‑tuned backbones show that SST consistently reduces forgetting and improves generalization, achieving up to a 5.75‑point performance gain and a dramatic drop in maximum forgetting from 42.41 to 7.10 points on the Qwen‑3B MATH stream.
The paper introduces HaMo, a Harness-Model collaborative framework designed for long-horizon continual learning. HaMo combines fast non‑parametric experience accumulation—distilling trajectories into strategy‑level experience cards for immediate retrieval—with slow parametric adaptation, training the model to interpret, ground, and execute these strategies across changing contexts. A retrieval‑coverage‑based selection mechanism identifies compact, complementary trajectories for parameter updates, and experiments demonstrate that HaMo outperforms both harness‑only and model‑only approaches in within‑domain and cross‑domain settings, improving retention and adaptation.
arXiv:2608. 06216v1 Announce Type: cross Abstract: Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.
arXiv:2606. 02461v2 Announce Type: replace Abstract: Language agents spend substantial inference time solving individual tasks, yet the experience acquired in one episode is often underutilized in future episodes.
arXiv:2606. 02461v1 Announce Type: new Abstract: Language agents spend substantial inference time solving individual tasks, yet the experience acquired in one episode is often underutilized in future episodes.
arXiv:2610.02150v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on persistent external sources to solve sequences of knowledge-intensive tasks. Existing methods...
The paper introduces Harness Continual Learning (HCL), a paradigm where an agent’s state evolves through prompts, memories, tools, skills, and routing rules while keeping the underlying foundation model frozen. HCL defines harness-level forgetting and proposes a guarded evolution process involving a Continual Optimizer and Evaluator to ensure improvements without losing prior behavior. Experiments across textual reasoning, multimodal perception, and open‑world interaction show over 10% performance gains and demonstrate how the stability–plasticity trade‑off can be explicitly tuned.