Do LLMs Act on What They Know? From Partner Representations to Cooperative Actions
Across eight LLMs, probes decode Hanabi partner conventions better than the models act on them.
Stories per day · 30 days
2 RSS
9 stories, newest first · one card per story
Stories tagged #qwen3-8b
Harness Engineering for Software Engineering via Modular Executable Dev-Primitives
HERMES uses modular Dev-Primitives to beat baseline software-engineering agent harnesses by 12.4% on four benchmarks.
Evaluating Biomedical Reranking for LLM-Based Question Answering over Longitudinal Clinical Notes
Biomedical reranking raised clinical-note Hit@10 from 46.6% to 60.6%, while Qwen3-8B correctness reached only 48.6%.
Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training
A 50,228-pair Agent Error Dataset diagnoses LLM agent failures and improves correction and post-training.
AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation
AdviSD trains a small advisor with selective self-distillation, beating advisor-GRPO on BFCL-v3 and EnvScaler.
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
A rank-8 LoRA lets frozen transformers follow much longer in-context reference chains.
AI models' written reasoning steps correspond to distinct internal patterns, a new study finds
KAIST and Naver AI Lab researchers show LLM reasoning steps like extraction and computation map to distinct activation patterns, strongest in middle layers.
3
You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs
Study quantifies DPO-tuned LLMs undershooting requested emotional intensity, tracing the gap to candidate-pool extremity rather than conditioning format.
Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal
A self-distillation safety framework tunes narrow-boundary refusals in Qwen3-8B, raising target-domain refusal to 84.75% while cutting over-refusal from 15.20% to 5.20%.