5 papers
The Delegation Danger Band: Why Mid-Capability Sub-Agents Over-Trust Inherited Stale State
Jundong Hu, Shekar Ramachandran
Agent frameworks increasingly delegate work by forking sub-agents; a common default makes the child inherit the parent's full working context. We measure how the effect of inherite…
XMerge: Cross-Axis Selection and Reconstructive Layer Merging for LLM Depth Compression
Jundong Hu, Shekar Ramachandran
Removing complete transformer layers preserves a standard serving architecture, but existing depth-compression methods can lose substantial quality, and the loss varies unpredictab…
Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?
Jundong Hu, Shekar Ramachandran
Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model (LLM) planner: auto-approving shell commands, writing…
The Memory Trust Gap: Capability-Dependent Failures in Persistent-Memory Agents
Jundong Hu, Shekar Ramachandran
Persistent memory supports personalized agents, but a stale stored fact can override current authoritative evidence without warning. We study when this harm begins as model capabil…
The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally
Jundong Hu, Shekar Ramachandran
Post-training quantization (PTQ) is widely used to reduce the cost of serving large language models (LLMs), but its accuracy cost is uneven and is often tuned per model. We study w…