ULTRADISCOVERY is a benchmark that tests abductive exploration in an epistemically open, interconnected universe. It features five domains where agents must revise an initial theory and predict outcomes of unseen cross‑domain interventions, with a $2 imes 2$ design manipulating representation openness and evidence alignment. Experiments show that agents struggle to compose evidence into transferable representations, especially when the representation is open, and that even with aids exact predictions are rare without large budgets.
arXiv:2609.01526v1 Announce Type: new Abstract: Scientific agents must learn not only how to reason, but also what to believe. However, existing LLM agents typically express scientific hypotheses in...
LongHarness is a model‑agnostic harness that explicitly manages the interaction between acquired evidence and evolving conclusions for long‑context reasoning over corpora larger than a model’s context window. Its Evidence‑Conclusion Coevolution mechanism uses unresolved conclusions to steer evidence retrieval, while new evidence refines those conclusions, and its Evidence Lifecycle Management keeps evidence current and traceable. Evaluations on OfficeQA Pro, AA‑LCR, and LongBench v2 show substantial performance gains over direct reasoning and state‑of‑the‑art agent harnesses, with GLM‑5.3‑Flash exact match improving from 15.8% to 60.2% on V1 and from 4.4% to 61.1% on V2.
The paper introduces LLM-IDEA, an identifiability‑driven experimental agent that guides large language model scientists in closed‑loop discovery of mechanistic world models. It incorporates an identifiability engine that classifies experimental plateaus as capability limits, resolvable within the design class, or certified exhausted, and demonstrates its effectiveness on benchmarks such as ODEBench, DiscoverPhysics, and a custom Alien Universe testbed. The agent’s ability to distinguish when further experimentation is futile versus when new designs are needed improves the efficiency and reliability of autonomous scientific discovery.
The paper examines three open-source agent harnesses—LangChain’s deepagents, Earendil’s pi, and DeepSeek’s dsh—each built from contrasting design philosophies. By analyzing their source code and commit histories, the authors find that the mature harnesses converge on five common architectural elements: a commoditized loop, an append‑only replayable session record, model quirks stored as data, progressive disclosure of context, and explicit extension seams. A fourth harness, used as a held‑out check, also displays all five elements and even reuses another’s implementation, indicating that convergence arises from parallel discovery, diffusion, and literal reuse rather than independent invention. The study notes a missing dimension—external verifiability via a tamper‑evident record—highlighting a future axis for provenance‑sensitive domains.
LLM-IDEA is an identifiability‑driven experimental agent that guides large language model scientists in autonomous discovery of mechanistic world models. It evaluates whether a plateau in learning is due to the agent’s capability limits, the model’s resolvability within the design class, or a certified exhaustion of the experiment space. The system demonstrates its effectiveness across benchmarks such as ODEBench, DiscoverPhysics, and a custom Alien Universe testbed, consistently identifying when additional experiments are futile and when new experimental designs are required.
An agent harness is what turns a language model into an autonomous agent: the surrounding code that builds the model's context, mediates its tools, runs the loop, and persists state across a long-hori...
arXiv:2607. 12267v1 Announce Type: cross Abstract: Language agents that interleave reasoning and tool use degrade sharply as reasoning chains lengthen, even when each individual step is easy.
The paper proposes a distributional theory explaining how large language models (LLMs) incorporate external evidence into their decision-making process. It identifies three key predictions: (1) evidence is more persuasive when it aligns with the model’s prior beliefs, (2) models more readily accept errors from their own internal processes than from external sources, and (3) the same evidence can improve weaker models while harming stronger ones. Extensive experiments across ten million trials, twelve LLMs from four families, and eight domains—including quantum mechanics, physics, genetics, and molecular biology—confirm these predictions and reveal that evidence integration occurs late in the network as a structured sequence of steps rather than through a simple trust metric.
Can scientific abduction occur without continuous sensorimotor embodiment? Recent arguments in AI and philosophy of science hold that genuine hypothesis generation requires an agent continuously coupled to the physical world.
arXiv:2605.26087v2 Announce Type: replace-cross Abstract: Frontier LLMs now perform strongly across a wide range of physics evaluations, but it is hard to disentangle genuine reasoning from recall of...
The paper treats human interventions during LLM agent failures as labels that pinpoint the internal computation that went wrong, rather than merely training data. In a controlled environment, the authors analyze one failure type—over‑asking a clarifying question when the request is already clear—using rule‑based overseer labels validated by blind human judgment. They find that the decision to ask versus act can be causally localized across several models, that over‑asking exhibits distinct mechanistic signatures, and that steering or weight consolidation can mitigate the issue, though outcomes vary by model family.
The paper audits whether synthetic distractors in RLVR corpora act as shortcuts for learning policies. A classifier using only surface statistics barely outperforms chance, and manual inspection reveals that code distractors are almost identical to correct answers. Experiments with a paraphrase‑matched control show no exploitation advantage for the unmodified data, indicating that the detectable artifact was not used by the policy.