OpenBioRQ: Unsolved Biomedical Research Questions for Agents

• URL: http://arxiv.org/abs/2606.21959v1
• Date: Sat, 20 Jun 2026 09:16:15 GMT
• Title: OpenBioRQ: Unsolved Biomedical Research Questions for Agents
• Abstract summary: I introduce textopenbiorq, a benchmark for unsolved biomedical research questions.<n>This is the first benchmark to combine an agentic setting -- where the model must issue multiple tool calls -- with unsolved questions that have no answer key.<n>I observe agentic collapse on the hardest questions, where agents stop using their tools.
• Score: 2.3677513428867614
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A working citation looks like proof -- but the fact that a link resolves does not mean the cited paper supports the claim. I find that current agentic models rarely fabricate citations (over $99\%$ resolve), yet roughly $15.9\%$ link to the wrong paper. Existing benchmarks miss this failure mode: when a question has a fixed answer key, a model can reproduce the expected source from that key rather than independently verifying that the source supports the claim. I introduce \textbf{\openbiorq{}}, a retrieval-grounded agentic benchmark of $12{,}553$ unsolved biomedical research questions across $12$ domains that treats open questions as a faithfulness-and-abstention probe. To my knowledge, this is the first biomedical benchmark to combine an agentic setting -- where the model must issue multiple tool calls -- with unsolved questions that have no answer key. Openness is verified against real follow-up evidence rather than a model's parametric knowledge. Difficulty is empirical: I anchor it on questions that three open-weight reference models fail to answer, rather than on subjective hardness labels. On this hardest subset, held-out models from the same lineage as the difficulty anchors solve only ~17%, while three independent frontier agents (Gemini-3-Pro, Opus-4.7, GPT-5.5) span a wide 29-60% range. The benchmark is thus hard, non-saturating (the best agent still leaves ~33-40\% unsolved), and discriminating across capability tiers. Beyond difficulty, I observe agentic collapse on the hardest questions, where agents stop using their tools. For the most collapse-prone model, blocking tool access entirely barely changes its score -- so tools stop paying off exactly where they are needed most. A frozen per-question checklist raises inter-judge agreement from Spearman 0.35 to 0.82.

Related papers

• TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards [15.908097225313968]
  Reinforcement learning with verifiable rewards (RLVR) has advanced language-model reasoning in domains such as mathematics and code.<n>We ask whether this asymmetry of verification can be engineered.<n>We instantiate this approach in TRACE, a digital-advertising diagnostic environment with 12 root causes and fine-grained segment attribution.
  arXiv  Detail & Related papers  (2026-09-09T15:21:47Z)
• Governance at the Boundary: How Agent Decomposition Degrades Policy Compliance [6.411104724993454]
  We introduce Fiducia-bench, a benchmark for the governability of financial agents.<n>We use it to study a question no prior benchmark addresses: does an agent degrade its governance?<n>Policy-relevant facts discovered by one component are attenuated at the handoff boundary before reaching the component that must act on them.
  arXiv  Detail & Related papers  (2026-08-17T03:31:59Z)
• When Self-Consistency Backfires: Majority Vote Hurts the Majority of Hard Science Problems for Small LLMs [0.0]
  Self-consistency via majority vote reduces per-problem accuracy on most GPQA Diamond problems for small instruction-tuned models.<n>This version reports that the most natural repair also fails, and separates three signal failures that v1 treated as one.
  arXiv  Detail & Related papers  (2026-08-11T20:08:51Z)
• AREX: Towards a Recursively Self-Improving Agent for Deep Research [75.96468303743958]
  We introduce AREX, a family of Recursively Self-Improving deep research agents.<n>AREX alternates between an inner research loop that gathers evidence and constructs a provisional answer.<n>We train AREX on verified synthetic tasks and high-quality trajectories through agentic mid-training and long-horizon reinforcement learning.
  arXiv  Detail & Related papers  (2026-07-23T16:05:46Z)
• MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning [47.751319722749116]
  textscMOCA-Agent is a market-of-claims code agent that replaces free-form multi-agent debate with claim-level verification.<n>The system decomposes each question into typed atomic claims, asks specialist trader agents to buy or sell those claims, clears their orders into confidence-weighted accept/reject decisions.<n>A code-aware verifier then checks the program for execution, structural consistency, and common financial reasoning errors.
  arXiv  Detail & Related papers  (2026-06-10T00:45:39Z)
• PBT-Bench: Benchmarking AI Agents on Property-Based Testing [29.035258104995204]
  We introduce PBT-Bench, a benchmark of 100 curated property-based testing problems across 40 real Python libraries.<n>Each problem injects one or more semantic bugs (365 in total, mean 3.65 per problem) designed so that default-strategy random inputs almost never trigger them.<n>Bug recall under the PBT-guided prompt ranges from 42.1% to 83.4% across models; under the open-ended baseline, from 31.4% to 76.7%.
  arXiv  Detail & Related papers  (2026-05-13T18:01:05Z)
• What Do EEG Foundation Models Capture from Human Brain Signals? [64.48249643001402]
  Modern EEG foundation models learn directly from raw signals via self-supervised pretraining.<n>We decompose into three sub-questions: emphwhat does the model learn, emphwhat does the model use, and emphhow much can be explained<n>The audit covers three foundation models (CSBrain, CBraMod, LaBraM), five clinical tasks (MDD, Stress, ISRUC-Sleep, TUSL, Siena), and a 6-family 63-feature lexicon.
  arXiv  Detail & Related papers  (2026-05-12T01:57:53Z)
• ClaimFlow: Tracing the Evolution of Scientific Claims in NLP [67.23189226608389]
  We introduce $texttClaimFlow$, a claim-centric view of the NLP literature.<n>We define a new task $-$ $textitClaim Relation Classification$ $-$ which requires models to infer the scientific stance toward a cited claim.<n>Our analysis reveals that $63.5$% claims are never reused; only $11.1$% are ever challenged.
  arXiv  Detail & Related papers  (2026-03-17T02:43:36Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Retrieval-Augmented Generation with Conflicting Evidence [57.66282463340297]
  Large language model (LLM) agents are increasingly employing retrieval-augmented generation (RAG) to improve the factuality of their responses.<n>In practice, these systems often need to handle ambiguous user queries and potentially conflicting information from multiple sources.<n>We propose RAMDocs (Retrieval with Ambiguity and Misinformation in Documents), a new dataset that simulates complex and realistic scenarios for conflicting evidence for a user query.
  arXiv  Detail & Related papers  (2025-04-17T16:46:11Z)
• UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models [55.22048505787125]
  This paper contributes a comprehensive dataset, called UNK-VQA. We first augment the existing data via deliberate perturbations on either the image or question. We then extensively evaluate the zero- and few-shot performance of several emerging multi-modal large models.
  arXiv  Detail & Related papers  (2023-10-17T02:38:09Z)
• Mitigating False-Negative Contexts in Multi-document QuestionAnswering with Retrieval Marginalization [29.797379277423143]
  We develop a new parameterization of set-valued retrieval that properly handles unanswerable queries. We show that marginalizing over this set during training allows a model to mitigate false negatives in annotated supporting evidences. On IIRC, we show that joint modeling with marginalization on alternative contexts improves model performance by 5.5 F1 points and achieves a new state-of-the-art performance of 50.6 F1.
  arXiv  Detail & Related papers  (2021-03-22T23:44:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.