3 papers
cs.IR2026
Search Engines Never Say No: How Frozen Agents React When the Retrieval Tool Refuses
Ramraj Chandradevan, Sayontan Ghosh, Vinoth Selvendran
A search tool never says no: it returns its top-k passages even when the index holds no answer, so the agent sees irrelevant text instead of a miss signal. We ask what frozen searc…
cs.LG2026
Sharpen Before You Adapt: Data-Free Entry-State Sharpening for Test-Time Reinforcement Learning
Zhanming Zhang, Vinoth Selvendran
Test-time reinforcement learning (TTRL) adapts language models on unlabeled test problems using supervision derived from their own samples. This makes the checkpoint's \emph{entry…
cs.AI2026
Beyond Uncertainty: Multi-Solver Disagreement Rewards for Self-Evolving Reasoning Curricula
Vinoth Selvendran, Zhanming Zhang
Self-evolving reasoning frameworks train a Challenger to generate questions exposing a Solver's weaknesses, creating adaptive curricula without human data. However, existing approa…