IdeaTrail: Full-Process Agent Trajectories for Scientific Ideation

• URL: http://arxiv.org/abs/2607.10144v2
• Date: Tue, 14 Jul 2026 06:41:48 GMT
• Title: IdeaTrail: Full-Process Agent Trajectories for Scientific Ideation
• Abstract summary: We introduce IdeaTrail, a dataset of 1,170 multi-turn trajectories for scientific ideation and proposal generation.<n>IdeaTrail is synthesized from human-selected research papers and proposal artifacts through a Generator-Advisor loop.<n>This reverse-to-forward design keeps trajectories aligned with real scientific artifacts while retaining the uncertainty, evidence use, and staged convergence characteristic of research practice.
• Score: 4.061135251278187
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scientific ideation unfolds over multiple stages, including literature search, paper reading, tool use, claim checking, cross-paper synthesis, brainstorming, rejection of weak directions, and iterative writing. Yet most existing resources capture isolated components or final artifacts rather than the process connecting them. We introduce IdeaTrail, a dataset of 1,170 multi-turn trajectories for scientific ideation and proposal generation. Each trajectory follows a research process from evidence gathering to either idea selection or proposal construction, jointly recording tool use, acquired evidence, intermediate artifacts, and reasoning. IdeaTrail is synthesized from human-selected research papers and proposal artifacts through a Generator--Advisor loop. The Generator produces the visible sequence of actions, observations, and artifact edits, while the Advisor uses the full generation context to check grounding, causal order, naturalness, and leakage from hidden targets. This reverse-to-forward design keeps trajectories aligned with real scientific artifacts while retaining the uncertainty, evidence use, and staged convergence characteristic of research practice. IdeaTrail provides both reusable process supervision and a general recipe for constructing scientific-research-agent data.

Related papers

• From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form Generation [49.496216822640974]
  RetroGen is a self-improving framework for retrospective process supervision.<n>It reconstructs latent trajectories from expert artifacts, verifies them against the artifact and supporting evidence, and trains models on their own successful reconstruction data.<n>Experiments show that RetroGen improves grounding, faithful synthesis, and long-form evidence-seeking agent tasks.
  arXiv  Detail & Related papers  (2026-08-31T08:47:39Z)
• Artifact-centered Claim-aware Observability for Autonomous Scientific Agents [4.403170275941483]
  We propose a compact observability profile organized around individuals, operators, fitness records, lineage, archives, runs, streams, and steering commands.<n>The profile is intended as a semantic layer that complements current telemetry and provenance standards.
  arXiv  Detail & Related papers  (2026-08-18T20:47:24Z)
• SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery [48.99744520105086]
  SciForge is a multimodal research-native AI workbench.<n>It reserves the graphical interface for human judgment while search, parsing, model routing, workflow execution, plotting, writing, and presentation generation run as modular agent-accessible services.
  arXiv  Detail & Related papers  (2026-07-17T15:13:03Z)
• XScientist: A Git-Like Research Protocol for Long-Running Autonomous Scientific Discovery [1.1923076571060318]
  XScientist is a git-like research protocol and operating system for autonomous research systems.<n>It orchestrates idea generation, experiment execution, manuscript drafting, self-review, repair, quality gating, daemon scheduling, and artifacts as one continuously observable pipeline.<n>It exports an Agent-Native Research Artifact protocol that records an exploration DAG, per-node code and outputs, claim-to-evidence anchors, content hashes, provenance, and re-execution hooks.
  arXiv  Detail & Related papers  (2026-07-14T03:20:11Z)
• Rethinking Scientific Discovery in the Agentic Era [69.85050591628048]
  SCION is an agentic scientific operating system that acts as an textbf organizational nexus.<n>At its core is the textbfResearch Execution Plan (REP), which compiles high-level scientific intent into staged objectives, dependencies, verification checkpoints, tool requirements, expected artifacts, and fallback conditions.<n>We formulate discovery under SCION as textbfTarget-conditioned Inverse Search and extend it to hidden-target settings through batch active search under finite experimental budgets.
  arXiv  Detail & Related papers  (2026-07-04T13:09:33Z)
• Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents [9.918296068965665]
  Ideation plays a pivotal role in scientific discovery.<n>Agentic-Ideation is a novel framework comprising an automated trajectory synthesis pipeline and a specialized agentic LLM trained for scientific ideation.
  arXiv  Detail & Related papers  (2026-06-30T07:07:51Z)
• Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation [74.0621258662676]
  We propose Ptah, a multi-agent harness for interleaved report generation.<n>Ptah orchestrates the lifecycle from user query to rendered web report through planning, research, and writing stages.<n>A verifier agent serves as the harness's acceptance function, enforcing factual grounding, citation fidelity, and cross-modal consistency throughout the workflow.
  arXiv  Detail & Related papers  (2026-05-28T12:40:34Z)
• Alien Science: Sampling Coherent but Cognitively Unavailable Research Directions from Idea Atoms [53.907293349123506]
  Large language models often fail at producing ideas that are both coherent and non-obvious to the current community.<n>We formalize this gap through cognitive availability, the likelihood that a research direction would be naturally proposed by a typical researcher.<n>We learn two complementary models: a coherence model that scores whether a set of atoms constitutes a viable direction, and an availability model that scores how likely that direction is to be generated.
  arXiv  Detail & Related papers  (2026-03-01T13:05:19Z)
• ScholarGym: Benchmarking Deep Research Workflows on Academic Literature Retrieval [11.41528830724814]
  We present ScholarGym, a simulation environment for reproducible evaluation of deep research on academic literature.<n>Built on a static corpus of 570K papers with deterministic retrieval, ScholarGym provides 2,536 queries with expert-annotated ground truth.
  arXiv  Detail & Related papers  (2026-01-29T12:51:44Z)
• DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing [53.85037373860246]
  We introduce Deep Synth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities.<n>We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization)<n>Our results demonstrate that agentic plan-and-write significantly outperform single-turn generation.
  arXiv  Detail & Related papers  (2026-01-07T03:07:52Z)
• WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research [73.58638285105971]
  This paper tackles textbfopen-ended deep research (OEDR), a complex challenge where AI agents must synthesize vast web-scale information into insightful reports.<n>We introduce textbfWebWeaver, a novel dual-agent framework that emulates the human research process.<n>Our framework establishes a new state-of-the-art across major OEDR benchmarks, including DeepResearch Bench, DeepConsult, and DeepResearchGym.
  arXiv  Detail & Related papers  (2025-09-16T17:57:21Z)
• ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference [19.363580418167114]
  We formalize multi-document scientific inference, a new task that extracts and aligns motivation, methodology, and experimental results across related papers.<n>We present ResearchPulse, an agent-based framework that integrates instruction planning, scientific content extraction, and structured visualization.<n>To support this task, we introduce ResearchPulse-Bench, a citation-aware benchmark of annotated paper clusters.
  arXiv  Detail & Related papers  (2025-09-03T15:45:03Z)
• Synthesizing Scientific Summaries: An Extractive and Abstractive Approach [0.5904095466127044]
  We propose a hybrid methodology for research paper summarisation. We use two models based on unsupervised learning for the extraction stage and two transformer language models. We find that using certain combinations of hyper parameters, it is possible for automated summarisation systems to exceed the abstractiveness of summaries written by humans.
  arXiv  Detail & Related papers  (2024-07-29T08:21:42Z)
• RerrFact: Reduced Evidence Retrieval Representations for Scientific Claim Verification [4.052777228128475]
  We propose a modular approach that sequentially carries out binary classification for every prediction subtask. We carry out two-step stance predictions that first differentiate non-relevant rationales and then identify supporting or refuting rationales for a given claim. Experimentally, our system RerrFact with no fine-tuning, simple design, and a fraction of model parameters fairs competitively on the leaderboard.
  arXiv  Detail & Related papers  (2022-02-05T21:52:45Z)

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.