arXiv AI July 1, 2026 By Louis Mouchon

Surprise as a Signal for Plasticity and Metacognition

arXiv:2606. 31495v1 Announce Type: new Abstract: We study a single idea across two settings: that a prediction-error signal, computed by a small predictor over the latent space of a frozen encoder, can serve both as a gate on plasticity and as a substrate for metacognition.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Sep 1

Kathleen Remembers: Length-Invariant One-Shot Recall Without Attention

arXiv:2608.30376v1 Announce Type: cross Abstract: Recurrent, attention-free sequence models share a structural weakness: a fading state cannot perform exact recall of something seen once, far in the...

By George Fountzoulas

arXiv AI

Sep 1

Parametric Multimodal User Memory: Storing What Captions Cannot Carry

arXiv:2608.28609v1 Announce Type: cross Abstract: A personalized agent needs a user memory: a persistent model of who its user is. Today it is almost always text -- transcripts and captions retrieved...

By Bojie Li, Noah Shi

llms agents multimodal

arXiv AI

Sep 4

Learning What Not to Forget: Long-Horizon Agent Memory from a Few Kilobytes of Learning

The paper introduces LRE (Learned Relevance Eviction), a lightweight, CPU‑only, language‑model‑free scorer that learns which parts of an agent’s interaction history are task‑critical and preserves them verbatim. In experiments, LRE matches or surpasses baseline eviction policies on accuracy‑cost trade‑offs, recovers 93% of full‑history accuracy, reduces worst‑case prompt size by 52%, and outperforms dense and token‑pruning encoders in conversational memory while being 295–1569× smaller. The method also achieves superior budgeted answer quality on LoCoMo reading and can be trained annotation‑free, recovering 95% of supervised scorer performance.

By Nusrat Jahan Lia, Aritra Mazumder

llms agents efficiency

arXiv AI

Jul 3

Procedural Memory Distillation: Online Reflection for Self-Improving Language Models

arXiv:2607. 01480v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR), along with recent selfdistillation variants such as SDPO, evaluates each rollout against a verifier and updates the policy from that episode-level signal.

By Ye Liu, Srijan Bansal, Bo Pang, Yang Li, Zeyu Leo Liu, Yifei Ming, Zixuan Ke, Shafiq Joty, Semih Yavuz

llms reinforcement-learning efficiency

arXiv AI

Jun 29

Supersede: Diagnosing and Training the Memory-Update Gap in LLM Agents

arXiv:2606. 27472v1 Announce Type: cross Abstract: Large language model (LLM) agents operate over long, multi-session interactions in which facts change: a user moves, a price updates, a plan is revised.

By Vedant Patel

llms agents reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 18

Decomposing Prediction Mechanisms for In-Context Recall

arXiv:2507. 01414v2 Announce Type: replace Abstract: We introduce a new family of toy problems that combine features of linear-regression-style continuous in-context learning (ICL) with discrete associative recall.

By Sultan Daniels, Dylan Davis, Dhruv Gautam, Wentinn Liao, Gireeja Ranade, Anant Sahai

llms efficiency

One email a morning, machine-written

Related stories

Kathleen Remembers: Length-Invariant One-Shot Recall Without Attention

Parametric Multimodal User Memory: Storing What Captions Cannot Carry

Learning What Not to Forget: Long-Horizon Agent Memory from a Few Kilobytes of Learning

Procedural Memory Distillation: Online Reflection for Self-Improving Language Models

Supersede: Diagnosing and Training the Memory-Update Gap in LLM Agents

Decomposing Prediction Mechanisms for In-Context Recall