Paper

TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework

Unreadunread

AI summary

arXiv:2606. 05570v1 Announce Type: new Abstract: Repository-level coding benchmarks face a trade-off between task difficulty and evaluation reliability: tasks that challenge frontier models often involve large codebases with incomplete test coverage, while human review does not scale.

Reading status

Priority

About this paper

Authors: Bobby Yan, Fredrik Kjolstad
Released: 2026-06-05 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, strong, class, under, eval, source, rate, does. Source: arxiv cs.CL (NLP).
arXiv: 2606.05570

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.