Skip to content

Author

Heng Ji

We have 6 of 13 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

When Do Language Models Add Value? Relative Competence in Hybrid Event Forecasting

When a forecasting system already has a prediction from a market, crowd, or statistical model, when should it use a language model? Standalone accuracy cannot answer this question because a less accurate model may still improve the existing forecast. We study this distinction through relative competence, separating a m...

Aditi Tiwari, Aashrith Bandaru, Heng Ji · 0 citations
#artificial intelligence Preprint Oct 2026

LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures

LLM-based agents are increasingly capable of generating complex 3D structures, with the potential to reshape how objects are designed and realized in the physical world. Yet, producing elegant geometry is fundamentally different from producing objects that can be built and perform their intended functions. Existing eva...

Jia-Teng Liu, Ru-Shi Wang, Cheng Qian et al. · 0 citations
Preprint Sep 2026

Does Video Memory Use What It Retrieves? A Causal Audit of Memory Specificity

Video models increasingly use memory to preserve information over long sequences, with the assumption that gains come from retrieving and using the correct past content. Standard memory ablations test whether memory helps, but not whether the retrieved content is responsible. We test this directly with read-time memory...

Aditi Tiwari, Akshit Bhalla, D. Prasad et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training

An unsuccessful LLM agent rollout contains more information than its final reward: the observations available to the agent, the actions it chose, and the environment's responses. Reusing this experience for learning requires identifying a decision to revise and testing a concrete alternative. We introduce the Agent Err...

Kun-Lun Zhu, Xu-Yan Ye, Yi-Bo Li et al. · 1 citation
#artificial intelligence Preprint Sep 2026

Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI

Across Harness-Bench and NewtonBench, full-bank meta-skills improve macro-average performance by 8.95 percentage points over no-skill construction, and 12.02 points over direct delivery of the same bank to the Target.

Cheng Qian, Kun-Lun Zhu, Bei-Bin Li et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Competence-Gated Pooling of Language Models and Priors for Event Forecasting

A competence gate is introduced that estimates domain-level source weights from resolved outcomes, shrinks uncertain estimates toward a global weight, and recalibrates the pooled forecast and provides a practical approach for selective model use based on measured marginal value.

Aditi Tiwari, Aashrith Bandaru, Heng Ji · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.