arXiv AI
Jul 24
Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents
arXiv:2607. 20972v1 Announce Type: new Abstract: Coding agents ship with one kind of memory: documents.
From Detecting Agency to Doing Work: Self-Caused Credit Builds a Durable Behavioral Self in a Minimal Spiking Agent
arXiv:2606. 30191v1 Announce Type: new Abstract: How does an agent that can tell self from world come to be durably shaped by that distinction?
Related stories
arXiv AI
Sep 24
Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents
The paper introduces Just-in-Time Memory (JitMem), a system that defers memory curation until a task is read, allowing a curator to synthesize task‑specific memory payloads based on the current query. Unlike traditional write‑time curation, JitMem retains raw trajectories and trains the curator using immediate task success, avoiding long‑horizon credit‑assignment issues. Experiments on ALFWorld, WebShop, and τ²‑bench show JitMem consistently outperforms both no‑memory agents and existing write‑time memory methods, with improvements of up to 16.3 absolute success‑rate points. whyItMatters":"By curating memory at read time, JitMem enables more effective, task‑adaptive recall that directly improves agent performance across diverse benchmarks."
arXiv AI
Aug 7
When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents
arXiv:2608. 05810v1 Announce Type: new Abstract: Self-evolving agents accumulate capability by distilling reusable skills from their execution trajectories, but we find this process is not monotonic: past a critical pool size, newly added skills degrade performance instead of improving it.
arXiv AI
Jul 1
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.
arXiv AI
Aug 25
CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories
arXiv:2608.22533v1 Announce Type: new Abstract: Autonomous computer-use agents are increasingly applied to long-horizon tasks requiring coordinated application calls, persistent state tracking, and v...
arXiv AI
Jul 23
The World Model Remembers, the Actor Forgets: Dream Rehearsal for Continual Model-Based RL
arXiv:2607. 19749v1 Announce Type: cross Abstract: Model-based reinforcement-learning agents of the DreamerV3 family forget catastrophically when trained on task sequences, even when an unbounded replay buffer preserves every earlier experience.
arXiv Machine Learning
Aug 4
RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
arXiv:2608. 02508v1 Announce Type: new Abstract: Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges.
arXiv Machine Learning
Jun 19
Sparsity, Superposition, and Forgetting: A Mechanistic Study of Representation Retention in Continual Learning
arXiv:2606. 20431v1 Announce Type: new Abstract: Continual learning (CL) systems often forget previously acquired knowledge, yet the mechanisms driving forgetting remain hard to isolate in practice because real datasets entangle many factors.
arXiv AI
Sep 7
Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents
arXiv:2609. 04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache.
arXiv Machine Learning
Sep 16
Anatomy of Associative Recall in Fixed-State Recurrences: A Matched-State Decomposition, an Interference Wall, and a Curriculum That Breaks It
arXiv:2609.16183v1 Announce Type: new Abstract: Fixed-state recurrences--linear attention and state-space models--are reported to lag behind attention on associative recall, but whole-architecture co...
arXiv AI
Aug 20
SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents
SkillGate is a method that trains agents to select the correct skill from a large slate during an episode by separating credit signals for skill selection and execution. It addresses the problem of selector credit starvation, where traditional outcome-rewarded RL fails to give sufficient credit to the skill-naming tokens, especially in long-horizon tasks. Experiments on five benchmarks show that SkillGate improves a 9B policy’s success rate from 40.8% to 53.2%, reduces exposure to misleading candidates, and requires fewer skill reads.
arXiv Machine Learning
Jul 15
Constructed Reality, Contested Priors: Decoupling and the Architecture of Cognitive Relapse Under the Free Energy Principle
arXiv:2607. 11958v1 Announce Type: new Abstract: Under the free energy principle, a predictive system does not observe reality directly; it maintains a generative model of the world and experiences that model's best current hypothesis.