Fast-Slow Training uses context optimization as fast weights alongside parameter updates as slow weights to achieve up to 3x better sample efficiency, higher performance, and less catastrophic forgetting than standard RL in continual LLM learning.
Title resolution pending
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 10roles
background 1polarities
background 1representative citing papers
FlowBot automatically induces LLM workflows through bilevel optimization with textual gradients, achieving competitive performance against human-crafted baselines.
Multi-objective genetic prompt optimization creates multi-turn deceptive datasets validated by humans, then detected with 0.89 recall using angular coverage, distance ratio, and linearity features in embeddings.
Training-free prompt optimization methods, including five new education-focused ones, surpass the strongest RL-trained baseline across five conditions on two OOD suites while showing distinct teaching behavior patterns.
A universal LLM optimizer for text artifacts achieves SOTA results on six tasks including tripling ARC-AGI accuracy and cutting cloud costs by 40% via cross-task transfer and side information.
NCCE reframes context engineering as instance-level recommendation via bootstrapped anchor contexts and a co-evolving neural collaborative filtering router that assigns specialized contexts per input.
EditFlow reconstructs temporal developer editing flows from code changes to benchmark and optimize AI code edit recommenders so they align with natural incremental reasoning rather than static snapshots.
Contrastive Reflection identifies error-anchored slices in agent traces, adds contrastive successes, and uses a Teacher LLM to generate prompt edits that are accepted only if they improve validation performance, raising HotpotQA exact-match from 51.4% to 60.4%.
Trace2Policy's EISR iteratively refines expert-derived rules into compiled Python code reaching 79.6% accuracy on skewed compliance tasks, outperforming one-shot LLM distillation and a deployed LLM baseline.
AIR excels on label-remapping classification tasks while KNN retrieval leads on closed-book QA and fine-tuning leads on structured extraction and event-order reasoning, showing task-dependent adaptation performance.
citing papers explorer
-
Contrastive Reflection for Iterative Prompt Optimization
Contrastive Reflection identifies error-anchored slices in agent traces, adds contrastive successes, and uses a Teacher LLM to generate prompt edits that are accepted only if they improve validation performance, raising HotpotQA exact-match from 51.4% to 60.4%.
-
Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents
Trace2Policy's EISR iteratively refines expert-derived rules into compiled Python code reaching 79.6% accuracy on skewed compliance tasks, outperforming one-shot LLM distillation and a deployed LLM baseline.