arXiv:2606. 17541v1 Announce Type: cross Abstract: Offline evaluation of agentic systems often collapses trajectories to terminal success, discarding information about partial progress and inducing widespread ties, creating substantial statistical inefficiency by reducing effective sample size and weakening the ability to distinguish systems.
arXiv:2606. 09115v1 Announce Type: new Abstract: Offline reinforcement learning (RL) offers a path to policy improvement from logged data alone, using historical returns or other measurable outcomes as world feedback.
arXiv:2607. 06624v1 Announce Type: new Abstract: We present AgentLens, a production-assessed benchmark for interactive code agents.
arXiv:2608. 15956v1 Announce Type: new Abstract: Agentic retrieval workflows produce query, retrieval, and stopping traces as a byproduct of answering questions.
arXiv:2607. 13418v1 Announce Type: cross Abstract: Recommender systems operate as Black-Boxes, leaving users and regulators unable to steer their outputs toward specific intentions or audit their behavior.
arXiv:2608. 12847v1 Announce Type: new Abstract: Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities, constraints, or environment state have changed.
Multi-turn tool-using agents must coordinate long-horizon tool sequences while tracking dialogue state and policy constraints. Existing approaches often separate inference-time orchestration from parameter-level learning, leaving tool selection weakly structured and preference updates vulnerable to train--deployment prompt mismatch.
arXiv:2607. 15606v2 Announce Type: replace Abstract: Synthetic sequential tabular data are increasingly used for privacy-preserving data sharing and data-driven research, but evaluating their fidelity remains difficult because temporal structure is easily lost under conventional tabular metrics.
arXiv:2602. 22638v2 Announce Type: replace Abstract: Route-planning agents powered by large language models (LLMs) have emerged as a promising paradigm for supporting everyday human mobility through natural language interaction and tool-mediated decision making.
arXiv:2607. 24800v1 Announce Type: cross Abstract: Adaptive retrieval promises to make knowledge-graph question answering more robust by letting a controller search, inspect neighborhoods, revise actions, and stop when evidence is sufficient.
arXiv:2603. 02650v2 Announce Type: replace-cross Abstract: Diffusion planners are a strong approach for offline reinforcement learning, but they can fail when value-guided selection favours trajectories that score well yet are locally inconsistent with the environment dynamics, resulting in brittle execution.
arXiv:2606. 12871v1 Announce Type: new Abstract: Search Agents (SAs) typically leverage large language models (LLMs) to support complex information-seeking tasks by autonomously exploring web sources and synthesizing information into comprehensive responses.
arXiv:2605. 07736v2 Announce Type: replace Abstract: Online goal recognition in continuous domains poses two central challenges: efficiently encoding large trajectories and effectively comparing them.