LLM agents in knowledge intensive question answering take retrieval and reasoning actions with incomplete knowledge about whether their current answer is uncertain, unsupported, or already complete. This produces two failure modes: committing to confident but unsupported answers, which hurts accuracy, and over-retrieving when the evidence in hand already suffices, resulting in wasted compute.
arXiv:2609.37236v1 Announce Type: new Abstract: An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested....
arXiv:2610.05437v2 Announce Type: replace Abstract: Computer-use agents need to capture procedural knowledge of how people use software. User telemetry offers a scalable source of this knowledge. How...
arXiv:2608. 07531v1 Announce Type: cross Abstract: Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence.
Retrieval-augmented generation improves knowledge-intensive question answering, but indiscriminate retrieval can introduce irrelevant evidence and unnecessary computation. We investigate whether verbalized confidence from black-box language models can serve as an actionable signal for retrieval routing.
arXiv:2607. 25600v1 Announce Type: cross Abstract: Retrieval-augmented generation improves knowledge-intensive question answering, but indiscriminate retrieval can introduce irrelevant evidence and unnecessary computation.
arXiv:2608.28675v1 Announce Type: cross Abstract: Video reasoning tasks such as grounded video question answering and temporal grounding require selecting temporal evidence that supports the query. I...
arXiv:2606. 04815v1 Announce Type: cross Abstract: Lifelong learning is essential for Large Language Model (LLM) agents operating in dynamic, interactive environments.
DualStake introduces a dual-path confidence calibration for deep research agents, adding step confidence elicitation after each retrieval step. The method shows that evidence confidence (E-Conf) after the final retrieval provides a stronger uncertainty signal than answer confidence (A-Conf), and that A-Conf is largely influenced by E-Conf. By applying margin‑clipped, confidence‑dependent stake rewards, DualStake aligns both E-Conf and A-Conf with answer correctness, improving calibration across multiple QA benchmarks without harming accuracy.
TutorTrace is a new dataset and behavioral abstraction pipeline that captures learners’ low‑level IDE telemetry to make their behavioral context visible and computable in real time. The dataset, collected across 480 students in two introductory Python courses, includes 180 K telemetry events, 13 633 behavioral segments, and 27 continuously computed metrics, and it underpins a taxonomy of learner activity before, between, and after AI queries. Preliminary classroom tests show that behavior‑aware prompts reduce the time between queries, and the system can predict upcoming queries with AUROC scores of .726 and .717 on two held‑out tasks.
An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested. Work on proactive agents mainly studies whether...
arXiv:2608. 05102v1 Announce Type: new Abstract: Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer.
arXiv:2607. 09623v1 Announce Type: cross Abstract: We present our submission to the QANTA 2026 shared challenge at the ICML 2026 Workshop on Efficient Multimodal Question Answering (EMM-QA).