9 papers
IMPLY: Physically Anchored Consistency for World-Model Rollouts
Aman Mehta, Riya Baviskar
A world model asked what happens if an object is pushed at several speeds produces several futures. If the model has the object in mind, those futures agree about it: each implies…
CALIPER: Clean Scenes Cannot Rank Physical Inference in Pretrained Visual Representations
Aman Mehta, Riya Baviskar
How far a pushed object slides depends on its mass and friction, which no single image reveals. Pretrained visual encoders are increasingly used as the perception front end of worl…
The Refusal Residue: When Probes Catch Alignment Faking and When They Don't
Aman Mehta
Alignment faking is dangerous because a model can appear compliant under monitoring while preserving behavior it would reveal when unmonitored. When no scratchpad is visible, behav…
Finding the Right Tables and Columns: A Benchmark and Corpus-Adaptive Embeddings for SQL Schema Retrieval
Qingcheng Zeng, Puxuan Yu, Aman Mehta +2
Retrieval in the SQL setting has largely been studied as the task of finding, within a large collection of SQL statements, the statement that answers a natural-language question. A…
Plans Fade Fast: Why Context Management Is Load-Bearing for LLM Agents
Aman Mehta, Anupam Datta
Context managers summarize or evict old messages so agents can operate beyond a finite window. This creates a reliability problem: removing history that still shapes the model's co…
When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents
Aman Mehta, Anupam Datta
Tool-using LLM agents make early choices about what to search for, which evidence to trust, and what to do next. A wrong early choice can steer every later tool call, so an agent m…
Dual-View Training for Instruction-Following Information Retrieval
Qingcheng Zeng, Puxuan Yu, Aman Mehta +2
Instruction-following information retrieval (IF-IR) studies retrieval systems that must not only find documents relevant to a query, but also obey explicit user constraints such as…
Confident and Wrong: Silent Semantic Failures in Coding Agents
Aman Mehta
As coding agents move into production workflows, teams need to know not only whether an agent completes a task, but whether its action can be trusted. We show that completion and t…
When Agents Disagree With Themselves: Behavioral Consistency as an Uncertainty Signal for LLM Agents
Aman Mehta
Running the same LLM agent on identical inputs yields 2.3-4.2 distinct action sequences per 10 runs; this behavioral variance constitutes a training-free, black-box uncertainty sig…