5 papers
Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite
Mohsen Arjmandi
An agentic coding system couples a language model to a harness: the tools, prompts and control flow that turn a chat model into an autonomous software engineer. Vendors ship harnes…
The LLM Proposes, the Executive Disposes: A Self-Verifying Agent Instrument that Dissociates Commitment Drift from Binding Drift in Long-Horizon Agents
Mohsen Arjmandi
How do you verify a long-horizon agent when its own state and self-reports are exactly what you cannot trust? We present an agent instrument built so that verification is structura…
Distractor-Aware Truncation: Disentangling Context-Length Effects from Signal Loss in Long-Context LLM Benchmarks
Mohsen Arjmandi
A standard claim in the literature on retrieval-augmented and memory-augmented language models is that shorter context is better when the relevant information is preserved. We test…
GRID: Grammar-Railed Decoding for Enterprise SQL Generation
Mohsen Arjmandi
Large language models can write SQL, but enterprise deployment demands more than plausible text: outputs must be syntactically valid, must respect per-role and per-schema policy, m…
Sensi: Learn One Thing at a Time -- Curriculum-Based Test-Time Learning for LLM Game Agents
Mohsen Arjmandi
Large language model (LLM) agents deployed in unknown environments must learn task structure at test time, but current approaches require thousands of interactions to form useful h…