SciTraj: Claim-grounded typed citation graph for tracing research trajectories in NLP, ML, and CV
Researchers introduce SciTraj, a corpus of 32,559 papers from NLP, ML, and Computer Vision (2015–2024) connected by 573,126 directed typed citation edges, where each edge is grounded to the specific claim sentence motivating the citation. Six relation types (four NLI-verified, two similarity-gated) capture how papers extend, dispute, or realize prior work, going beyond homogeneous citation graphs. The corpus includes 287M typed trajectories and a temporally split link-prediction benchmark, enabling analysis of disciplinary siloing and topic emergence patterns. Findings highlight concentrated growth in Vision and LLM-related work.
Related guides (1)
Related events (8)
VeriTrace: Cognitive-Graph Framework with Explicit Regulatory Loops for Deep Research Agents
VeriTrace introduces a cognitive-graph framework for deep research agents that replaces implicit LLM reasoning over intermediate representations with three explicit regulatory loops: interpretive update, deviation feedback, and schema revision. The system addresses contamination and error propagation in evolving mental models during complex multi-step research tasks. Using Qwen3.5-27B backbones, VeriTrace improves over the strongest matched baseline by 4.22 pp on DeepResearch Bench Insight and 5.9 pp Overall win rate on DeepConsult. With Config-DeepSeek, it achieves the strongest reproducible open-source result on DeepResearch Bench.
CoTrace: A Goal-Level Attribution Framework for Measuring AI Contributions in Human-AI Collaboration
Researchers introduce CoTrace, a framework that decomposes explicit goals into verifiable requirements and traces both direct and indirect AI contributions across dialogue turns in human-AI collaboration. Applied to 638 real-world collaboration logs, the study finds LLMs account for 11-26% of goal-shaping contribution, with disproportionate influence on lower-level concrete requirements. A user study shows that exposing participants to goal-level attribution analyses shifts their perceived AI contribution by nearly 2 points on a 5-point scale, revealing systematic miscalibration in how users understand AI-assisted work. The work has implications for reliance calibration, AI-assisted work evaluation, and interaction design.
LongTraceRL: Reinforcement Learning for Long-Context Reasoning via Search Agent Trajectories and Rubric Rewards
LongTraceRL is a new RL training framework for improving long-context reasoning in LLMs, addressing limitations of existing RLVR methods. It constructs challenging training data using multi-hop questions from knowledge graph random walks and tiered distractors derived from search agent trajectories (high-confusability: read but uncited; low-confusability: seen but unopened). A rubric reward provides entity-level process supervision along reasoning chains, applied only to correct responses to prevent reward hacking. Experiments across three LLMs (4B–30B parameters) on five long-context benchmarks show consistent improvements over strong baselines.
Tracking Behavioral Trajectories of Adapting Agents via Trait Vectors in Embedding Space
This paper introduces a methodology for measuring behavioral traits of AI agents by defining traits as directions in the embedding space of a text embedding model, trained on labeled diffs of agent skill/memory/configuration files. A linear model achieves 91.2% sign classification accuracy and Spearman ρ=0.82 on detecting propensity to seek sensitive data across 68 labeled skill diff pairs. The framework extends to an agent-to-agent evaluation protocol where one agent can assess another's skill file updates through a trusted intermediary, enabling ongoing behavioral monitoring of self-modifying agents.
ModSleuth: Agentic system audits invisible dependency graphs in modern LLM training pipelines
Researchers introduce ModSleuth, an agentic system that recursively reconstructs LLM dependency graphs from public artifacts, recovering 1,060 source-verified dependencies across four major LLM releases. The system formalizes direct and indirect dependencies and operation-centered relationships to handle fragmented, inconsistent documentation. Applied at scale, the resulting graphs expose multi-hop license obligations, train-evaluation coupling, and discrepancies between released and training-time artifacts — issues that are practically invisible to manual auditing.
TrajTok: Adaptive Spatial Tokenization for Trajectory Representation Learning
TrajTok is a trajectory encoder that learns transferable GPS trace representations via multi-resolution hexagonal spatial tokenization and masked-token pretraining. It uses a factorized transformer with per-modality self-attention, cross-attention fusion, and spatiotemporal rotary position embeddings (ST-RoPE) to jointly encode geometry and kinematics. A single frozen TrajTok encoder with lightweight adapters outperforms task-specific methods on trajectory similarity search, classification, ETA, and travel-time regression on the Porto dataset. The work positions learned spatial tokenization plus masked pretraining as a viable path toward general-purpose trajectory foundation models.
DocTrace: Structure-Aware On-Demand Hypergraph Memory for Long-Document QA
Researchers introduce DocTrace, a multi-agent RAG framework for long-document question answering that uses query-triggered knowledge organization rather than costly query-agnostic preprocessing. The system combines a lightweight document structural tree index, on-demand hypergraph working memory, and a graph-structured experience memory that stores successful reasoning plans for reuse. Evaluated on four long-document QA datasets, DocTrace outperforms the strongest baseline (ComoRAG) by up to 8.85% F1 and 4.40% EM while reducing computational cost by 53.32%.
SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics
SPECTRA is a reproducible framework for generating synthetic information retrieval test collections, separating latent topical structure, surface text realization, and query intent generation to produce deterministic relevance oracles without human annotation. A Python prototype generated corpora up to 60,000 documents at roughly 12K–14K documents per second, with graded relevance labels for 96 queries. Controlled distractor experiments showed BM25 nDCG@10 degrading from 1.00 at 2% distractors to 0.43 at 36%, demonstrating the framework's utility for exposing retrieval system failure modes before expensive real-world collection construction. The authors position SPECTRA as a diagnostic complement to Cranfield/TREC-style evaluation rather than a replacement for human judgment.