5 papers
Can LLMs Separate Pasted Artifacts from User Speech? Absorption at Unmarked Prompt Seams
Sugam Panthi, Muhaiminul Yeamin, Rabab Abdelfattah
Large language models (LLMs) receive each user message as plain text, even when it combines text from different sources. For example, a user may paste text into a prompt and keep t…
Memory Consolidation Flattens the Temporal Shape of User Facts
Sugam Panthi, Muhaiminul Yeamin, Siyan Luo +1
Long-term memory systems turn conversations into short stored notes. A note can keep a user fact while losing evidence about whether the fact still holds. For example, "I am drivin…
Outcome Monitors: Recovery Affordances for Silent Tool Failures
Sugam Panthi, Rabab Abdelfattah
When a tool call times out, the agent sees the failure and can route around it. A cached error page or negative price can instead arrive in the expected format and be consumed as f…
Compression Is Not Evaluation-Neutral: Fixed RAG Compression Can Distort Reader Comparisons
Sugam Panthi, Rabab Abdelfattah
Retrieval-augmented generation (RAG) evaluations often compare readers after a compressor has changed their evidence. This mixes two questions: which complete pipeline works best,…
Same Ranking, Different Winner: How Scoring Targets Shape LLM Memory Benchmarks
Sugam Panthi, Rabab Abdelfattah
Conversational-memory systems increasingly transform dialogue history into facts, summaries, timelines, and other source-linked descendants, so a single source turn can coexist wit…