arXiv:2606. 11522v1 Announce Type: new Abstract: Autoresearch agents now propose, evaluate, and select scientific candidates against a metric, and that metric is usually an aggregate reduced over a heterogeneous space of regions, slices, or cohorts.
arXiv:2608. 05212v1 Announce Type: new Abstract: Deep search agents tackle challenging questions through long-horizon web interactions, a process that is both complex and fragile: small reasoning errors may propagate through long, noisy trajectories into fluent but incorrect answers.
arXiv:2608. 13564v1 Announce Type: new Abstract: Evaluating language-model agents at scale increasingly relies on a second language model as an automatic judge, because the gold signal, an executable environment reward, is expensive, slow, or unavailable at deployment time.
arXiv:2608. 09855v1 Announce Type: new Abstract: Autonomous research agents can generate experiments faster than researchers can validate them.
arXiv:2606. 00408v1 Announce Type: cross Abstract: Long-horizon search agents accumulate large amounts of retrieved content across many tool calls, making context-budget efficiency increasingly important.
arXiv:2606. 29194v1 Announce Type: new Abstract: Automated alpha mining holds the scoring function fixed and varies the search algorithm over it.
arXiv:2607. 25152v1 Announce Type: new Abstract: Long-running autonomous agents plan, act, and judge their own completion without human intervention.
arXiv:2607. 22682v1 Announce Type: new Abstract: We introduce a vocabulary for automated research systems built from one or more agents to make their design choices easier to describe and compare.
arXiv:2608. 06422v1 Announce Type: new Abstract: Giving an LLM judge more compute does not necessarily make it check more requirements.
arXiv:2606. 10241v1 Announce Type: new Abstract: Autonomous improvement loops are hard to trust because the improvement process is usually external scaffolding bolted onto the agent: failures go unlogged, diagnoses cannot be replayed, and promote-or-discard decisions land in a side database rather than the agent's own history.
arXiv:2608. 06949v1 Announce Type: new Abstract: Prior benchmarking work has shown that a single large language model (LLM), forced to make life-or-death resource-allocation decisions, exhibits measurable demographic bias.
arXiv:2606. 12834v1 Announce Type: new Abstract: As scientific workflows shift from deterministic executables to LLM-based agents, the development practices on offer, such as fine-tuning, reinforcement learning, and prompt-and-go, bury the scientist's judgment.
arXiv:2607. 21268v1 Announce Type: cross Abstract: In many social-science research tasks, such as economics, LLM-based agents must produce outputs for which no cheap, task-complete, machine-readable correctness signal exists.