Causal diagnosis identifies the routing module as bottleneck in LLM agents but prompt patching there degrades results due to linguistic co-adaptation, while upstream patching improves them.
Trace is the next AutoDiff: Generative optimiza- tion with rich feedback, execution traces, and LLMs
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4roles
background 2polarities
background 2representative citing papers
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.
MOCHA combines Chebyshev scalarization with exponential annealing to optimize LLM agent skills across performance and platform constraints, improving mean correctness by 7.5% over baselines on six tasks while finding more Pareto-optimal variants.
citing papers explorer
-
Diagnosis Is Not Prescription: Linguistic Co-Adaptation Explains Patching Hazards in LLM Pipelines
Causal diagnosis identifies the routing module as bottleneck in LLM agents but prompt patching there degrades results due to linguistic co-adaptation, while upstream patching improves them.
-
Learning, Fast and Slow: Towards LLMs That Adapt Continually
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.
-
MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization
MOCHA combines Chebyshev scalarization with exponential annealing to optimize LLM agent skills across performance and platform constraints, improving mean correctness by 7.5% over baselines on six tasks while finding more Pareto-optimal variants.
- Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace