{"total":14,"items":[{"citing_arxiv_id":"2605.23204","ref_index":100,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","primary_cat":"cs.AI","submitted_at":"2026-05-22T03:40:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A survey organizing AI-powered research automation into five workflow stages, defining AutoResearch and Vibe Research, and proposing five evaluation dimensions while noting domain-conditioned limits on autonomy.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"discussion can generate more text without generating meaningfully stronger scientific distinction. • 3) Structure-guided ideation.This regime strengthens planning by imposing explicit scientific structure on the idea-formation process. Its workflow is closer tostructured grounding→principle / graph / facet-guided proposal formation→constrained candidate synthesis.Scideator[100] is a representative anchor because it grounds scien- tific ideation in research-paper facet recombination, allowing users to explore candidate directions by recombining purposes, mechanisms, and evaluations extracted from prior work.SciAgents[78] also belongs here because it uses graph-grounded scientific reasoning to represent and exploit cross-paper relations for hypothesis generation."},{"citing_arxiv_id":"2605.15011","ref_index":32,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"The Scientific Contribution Graph: Automated Literature-based Technological Roadmapping at Scale","primary_cat":"cs.CL","submitted_at":"2026-05-14T16:12:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Builds a 2M-contribution graph from 230k papers with 12.5M prerequisite links and reports 0.48 MAP on temporal backtesting for predicting enabling technologies.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13776","ref_index":54,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"\"Like Taking the Path of Least Resistance\": Exploring the Impact of LLM Interaction on the Creative Process of Programming","primary_cat":"cs.HC","submitted_at":"2026-05-13T16:54:51+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LLM assistance shortens idea-generation periods and reduces creative moments during programming tasks while yielding solutions with comparable idea counts and greater functional correctness.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"We adopted a semantic embedding approach using the Voyage Code 3 embedding model, which projects different surface representations (executable code, pseudocode, natural language) into a shared vector space where proximity reflects semantic similarity in the algorithmic approach. This addresses the limitation of traditional syntactic metrics like CodeBLEU [54], which assume well-formed, parseable code and would fail on pseu- docode or natural language descriptions present in our unassisted solutions. For each of the 80 solutions, we generated a 1024-dimensional embedding vector and computed pairwise cosine similarity between all solution pairs within each condition, separately for Algorithmic tasks and System Design tasks."},{"citing_arxiv_id":"2606.09851","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ECHO: Explainable Co-editing with Human-in-the-loop Operations for Presentation Refinement","primary_cat":"cs.HC","submitted_at":"2026-05-11T08:00:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ECHO presents a multimodal co-editing system and CoEdit-Eval framework that improves AI intent mapping and spatial grounding for presentation refinement while reducing user cognitive load in a small study.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04922","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation","primary_cat":"cs.MA","submitted_at":"2026-05-06T13:50:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"EIG represents research ideas as evolving graphs with nodes for claims and edges for relations, using a learned controller for edits and commits to produce higher-quality scientific proposals than text-only multi-agent baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23593","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"When AI reviews science: Can we trust the referee?","primary_cat":"cs.AI","submitted_at":"2026-04-26T08:03:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AI peer review systems are vulnerable to prompt injections, prestige biases, assertion strength effects, and contextual poisoning, as demonstrated by a new attack taxonomy and causal experiments on real conference submissions.","context_count":1,"top_context_role":"background","top_context_polarity":"unclear","context_text":", et al. (2024). Lan- guage agents achieve superhuman synthesis of scientific knowledge. arXiv preprint. DOI:10.48550/arXiv. 2409.13740 [41] Lin E., Peng Z. and Fang Y . (2025). Evaluating and enhanc- ing large language models for novelty assessment in schol- arly publications. Proc. Workshop AI Sci. Discov. 2025:46-57. DOI:10.18653/v1/2025.aisd-main.5 [42] Radensky M., Shahid S., Fok R., et al. (2024). Scideator: Human-llm scientific idea generation grounded in research-paper facet recombination. arXiv preprint. DOI:10. 48550/arXiv.2409.14634 [43] Couto P .H., Ho Q.P ., Kumari N., et al. (2024). Relevai- reviewer: A benchmark on AI reviewers for survey paper relevance. arXiv preprint. DOI:10.48550/arXiv."},{"citing_arxiv_id":"2604.11538","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"ResearchCube: Multi-Dimensional Trade-off Exploration for Research Ideation","primary_cat":"cs.HC","submitted_at":"2026-04-13T14:32:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ResearchCube provides a 3D spatial interface with bipolar trade-off dimensions and direct-manipulation interactions to support multi-dimensional research ideation, shown helpful in a study with 11 researchers for externalizing thinking and increasing agency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08898","ref_index":49,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Omakase: proactive assistance with actionable suggestions for evolving scientific research projects","primary_cat":"cs.HC","submitted_at":"2026-04-10T03:05:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Omakase monitors project documents to infer timely queries and distills research reports into actionable suggestions that users rated significantly more useful than raw reports.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"The two most common user interaction paradigms for literature- based research support are 1) Querying a deep research system that leverages LLM's reasoning powers to synthesize many retrieved documents; and 2) Recommender systems that proactively send paper recommendations to their users based on a list of seed papers. Deep research systems (e.g., [49]) have the potential of leverag- ing LLMs to understand the user's rich ongoing context. However, the dominant request-response paradigm can be prohibitively la- borious for users in two ways. First, it can be effortful tocompress the rich context of a complex project down to detailed instructions. Recent findings indicate that, while users increasingly add more"},{"citing_arxiv_id":"2604.02600","ref_index":40,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape","primary_cat":"cs.HC","submitted_at":"2026-04-03T00:22:08+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LitPivot introduces literature-initiated pivots where engagement with dynamically retrieved papers prompts revisions to a developing research idea.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"idea facets with literature-grounded feedback. InProceedings of the 2025 CHI Kambhamettu et al. Conference on Human Factors in Computing Systems. 1-31. [39] Marissa Radensky, Simra Shahid, Raymond Fok, Pao Siangliulue, Tom Hope, and Daniel S Weld. 2024. Scideator: Human-llm scientific idea generation grounded in research-paper facet recombination.arXiv preprint arXiv:2409.14634(2024). [40] Orit Shaer, Angelora Cooper, Osnat Mokryn, Andrew L Kun, and Hagit Ben Shoshan. 2024. AI-Augmented Brainwriting: Investigating the use of LLMs in group ideation. InProceedings of the 2024 CHI Conference on Human Factors in Computing Systems. 1-17. [41] Nihar B Shah, Behzad Tabibian, Krikamol Muandet, Isabelle Guyon, and Ulrike Von Luxburg. 2018. Design and analysis of the NIPS 2016 review process."},{"citing_arxiv_id":"2603.01092","ref_index":7,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions","primary_cat":"cs.AI","submitted_at":"2026-03-01T13:05:19+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A framework decomposes LLM papers into idea atoms, trains coherence and availability models over the resulting vocabulary, and samples atom combinations that are coherent yet unlikely under existing author communities.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.00361","ref_index":53,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers","primary_cat":"cs.HC","submitted_at":"2025-10-01T00:07:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Attribution gradients consolidate citation evidence and enable incremental unfolding of secondary sources, leading to deeper engagement in a lab study of critical reading tasks for AI answers.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.15736","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"IDRBench: Understanding the Capability of Large Language Models on Interdisciplinary Research","primary_cat":"cs.CL","submitted_at":"2025-07-21T15:43:05+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.11810","ref_index":144,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","primary_cat":"cs.DL","submitted_at":"2025-07-16T00:11:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The paper proposes a four-role framework for LLMs in scientific innovation and reviews methods, benchmarks, and limitations across Assistant, Collaborator, Scientist, and Evaluator roles.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[146] concentrates on scientific agents and their architectures, and Zhang et al. [222] primarily provides an inventory of LLM applications in diverse scientific domains. Within surveys attempting comprehensive coverage, several adopt a process-oriented perspective, examining how LLMs apply to different research stages without abstracting the hierarchical roles and capability boundaries of LLMs. For example, Reddy and Shojaee [144] reviews current LLM advances in literature analysis and brainstorming, theorem proving, experimental design, and data-driven discovery. Similarly, Luo et al. [116] explores LLM in the stages of hypothesis generation, experimentation, writing, and peer review, while Zhou et al. [233] investigates the phases of hypothesis construction, validation, and publication."},{"citing_arxiv_id":"2505.20779","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"CHIMERA: A Knowledge Base of Scientific Idea Recombinations for Research Analysis and Ideation","primary_cat":"cs.CL","submitted_at":"2025-05-27T06:36:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CHIMERA is the first large-scale mined KB of concept recombinations from scientific literature, created via a new IE task and LLM extraction, with demonstrated uses in pattern analysis and hypothesis generation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}