AEL uses a fast-timescale bandit for memory policy selection and slow-timescale LLM reflection for causal insights, achieving a Sharpe ratio of 2.13 on a 208-episode portfolio benchmark while showing that added mechanisms degrade performance.
Advances in Neural Information Processing Systems , volume=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
A memory-layer defense called Memory Sandbox stops persistent memory attacks on most LLM agents while other layer defenses fail.
Compiling agentic workflows into LLM weights creates subterranean agents with near-frontier quality at two orders of magnitude less cost, validated empirically on travel booking, Zoom support, and insurance claims tasks.
Injecting noise into LLM latent trajectories creates diverse reasoning paths whose agreement acts as a confidence signal for selective abstention, cutting error rates from 40-70% to under 15% on math tasks.
citing papers explorer
-
AEL: Agent Evolving Learning for Open-Ended Environments
AEL uses a fast-timescale bandit for memory policy selection and slow-timescale LLM reflection for causal insights, achieving a Sharpe ratio of 2.13 on a 208-episode portfolio benchmark while showing that added mechanisms degrade performance.
-
Defense effectiveness across architectural layers: a mechanistic evaluation of persistent memory attacks on stateful LLM agents
A memory-layer defense called Memory Sandbox stops persistent memory attacks on most LLM agents while other layer defenses fail.
-
Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost
Compiling agentic workflows into LLM weights creates subterranean agents with near-frontier quality at two orders of magnitude less cost, validated empirically on travel booking, Zoom support, and insurance claims tasks.
-
NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning
Injecting noise into LLM latent trajectories creates diverse reasoning paths whose agreement acts as a confidence signal for selective abstention, cutting error rates from 40-70% to under 15% on math tasks.