The paper introduces Metacognitive Memory Policy Optimization (MMPO), a novel memory training approach that optimizes LLM memory not based on final task success, but on minimizing epistemic uncertaint…

The paper introduces Canonical-Context On-Policy Distillation (CCOPD) to improve multi-turn language model performance by mitigating 'self-anchored drift,' ensuring consistent answers regardless of wh…

The paper introduces AGENTCL, a rigorous evaluation framework that uses controlled task streams to accurately measure an agent's ability to accumulate and reuse knowledge across multiple tasks, thereb…

The paper introduces Reasoning in Memory (RiM), a latent reasoning method that replaces autoregressive token generation with fixed memory blocks to enable compute-efficient internal working memory for…

This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

The paper identifies five persistent, deep-seated behavioral patterns ('training strata') in LLMs, observed through long-term, intimate human-AI interaction, suggesting that training artifacts survive…

The paper introduces StreamSynth, a sequential setting for synthetic data generation, and proposes SynLearner, a framework that enables LLMs to improve synthesis performance by accumulating and transf…

The paper introduces Temperature-Scaled On-Policy Self-Distillation (TS-OPSD), a novel method that internalizes temperature-based policy reheating into model parameters to combat entropy collapse in r…

The OISD framework improves language model reasoning by distilling on-policy predictive signals from the final output layer to intermediate representations, leading to substantial improvements on math…

MemGuard introduces a type-aware memory framework to prevent heterogeneous memory contamination in long-term memory-augmented LLMs, significantly improving memory reliability and efficiency.

The JAMEL framework addresses the challenge of effective exploration in open-ended environments by jointly training agent memory and exploration policies using natural, novelty-driven signals.

The paper investigates the limits of self-evolution in LLM reasoning under closed-loop settings, finding that while self-improvement is significant, it consistently falls short of perfect oracle super…

This survey establishes persistent, writable memory as an independent security problem for LLM agents, proposing a comprehensive framework for 'mnemonic sovereignty' to govern the entire memory lifecy…

SHARP proposes a novel sleep-based hierarchical replay framework to efficiently learn long-range non-stationary temporal patterns in streaming data, achieving improved context retention and predictive…

The paper proposes a comprehensive framework for LLM-based agent unlearning, enabling agents to selectively forget specific knowledge (states, trajectories, or environments) while maintaining performa…

This paper investigates how different types of compressed reasoning data (Explicit, Composed, Implicit CoT) affect LLM performance during post-training, finding that the choice of compression and subs…

The paper introduces Responsible Contrastive Soft Prompting (RCSP), a parameter-efficient method using soft prompts to improve LLM reliability by simultaneously suppressing hallucinations, encouraging…

The paper reframes context distillation as a latent memory management problem, proposing a modular framework using LoRA adapters and a Self-Gating mechanism for efficient, selective memory retrieval a…