Hao-Dong Chen

Search, Inspect, Fetch: Exploiting Boolean Retrieval for Deep-Research Agents

ITER: Interaction-Aware Retrieval for Agentic Search

Deep-research agents answer complex user questions through an iterative sequence of search steps, where the agent autonomously formulates sub-queries to retrieve the evidence needed at each stage. However, existing retriever training typically relies only on the sub-query and its corresponding search results at the current step as training signals, leaving the information accumulated from previous interactions largely underutilized. We introduce iter, an agent interaction-aware dense retriever trained using agent trajectory learning signals. iter represents each query by incorporating not only the current sub-query, but also the main question and preceding sub-queries, and is trained using trajectory-relative learning signals derived from the agent's interactions. Across six agent backbones from three model families, iter consistently outperforms the existing agent-trajectory-trained dense retriever, LRAT, achieving an average improvement of 7.5% on InfoSeek-Eval and 13.5% on BrowseComp-Plus. iter also demonstrates stronger cross-agent robustness than AgentIR, a deep-research retriever that relies on external LLM-judge signals and the agent's pre-search reasoning. Ablations further show that the main question and previous sub-queries provide the most robust query representation, while previously visited and useful documents, used as redundancy negatives in subsequent searches, provide the strongest trajectory-relative supervision. Code is available at https://github.com/ielab/ITER.

Beyond Dense States: Sparse Transcoders as Causally Testable Operators for LLM Latent Reasoning

LSTR (Latent Sparse Transcoder Reasoning), a framework that turns sparse transcoders from post-hoc diagnostic tools into in-loop, intervenable transition components for latent reasoning, and suggests that sparse latent transitions can preserve the compression benefits of latent reasoning while making the resulting trajectories more inspectable and intervenable.

Knowing but Not Saying: Preventing Factual Access Failures in LLM SFT via Recall-Anchored Distillation

Recall-Anchored Distillation (RAD), a base-anchored self-distillation objective that preserves out-of-distribution generation behavior by aligning the adapted model with the original base model's soft continuation distribution on unlabeled OOD text, is introduced.

Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Search Agents

This work introduces Sieve, a search-inspect-fetch strategy driven by a Boolean Query Language (BQL): it searches webpage fields to filter candidates, uses an interchangeable ranker to order them, presents structure-rich result cards for inspection, and fetches only selected sections.