New Links | ML News

ML Newsnew | past | best | rss | submit

1531.	Prompt Repetition Improves Non Reasoning LLM (arxiv.org)
	2 points by jdthedisciple 229 days ago \| hide \| past \| pdf \| discuss
1532.	GLM-5 Technical Report (arxiv.org)
	12 points by meetpateltech 229 days ago \| hide \| past \| pdf \| discuss
1533.	Training-Free Group Relative Policy Optimization (arxiv.org)
	1 point by readitalready 229 days ago \| hide \| past \| pdf \| discuss
1534.	Composition-RL: Compose Verifiable Prompts for Reinforcement Learning of LLMs (arxiv.org)
	3 points by gmays 229 days ago \| hide \| past \| pdf \| discuss
1535.	Randomness in Agentic Evals (arxiv.org)
	1 point by andre15silva 230 days ago \| hide \| past \| pdf \| discuss
1536.	Hunt Globally (arxiv.org)
	1 point by salkahfi 230 days ago \| hide \| past \| pdf \| discuss
1537.	Frontier Models Exhibit Sophisticated Reasoning in Simulated Nuclear Crises (arxiv.org)
	1 point by salkahfi 230 days ago \| hide \| past \| pdf \| discuss
1538.	Learning State-Tracking from Code Using Linear RNNs (arxiv.org)
	2 points by jul8234 230 days ago \| hide \| past \| pdf \| 1 comment
1539.	A Survey of In-Context Reinforcement Learning (arxiv.org)
	2 points by handfuloflight 230 days ago \| hide \| past \| pdf \| discuss
1540.	Soft Contamination Means Benchmarks Test Shallow Generalization (arxiv.org)
	2 points by cjbarber 230 days ago \| hide \| past \| pdf \| 1 comment
1541.	SkillsBench: Benchmarking how well agent skills work across diverse tasks (arxiv.org)
	364 points by mustaphah 230 days ago \| hide \| past \| pdf \| 171 comments
1542.	Virtual Width Networks (VWN) (arxiv.org)
	9 points by tesserato 230 days ago \| hide \| past \| pdf \| discuss
1543.	CodeLogician: Neuro-symbolic reasoning for precise software analysis (arxiv.org)
	2 points by NTCTech 231 days ago \| hide \| past \| pdf \| 1 comment
1544.	Delegated Agent Authorization Constrained to Semantic Task-to-Scope Matching (arxiv.org)
	1 point by mooreds 231 days ago \| hide \| past \| pdf \| discuss
1545.	Evaluating AGENTS.md: are they helpful for coding agents? (arxiv.org)
	232 points by mustaphah 231 days ago \| hide \| past \| pdf \| 161 comments
1546.	Multi-Agent Teams Hold Experts Back (arxiv.org)
	1 point by fauigerzigerk 231 days ago \| hide \| past \| pdf \| discuss
1547.	Large Language Model Reasoning Failures (arxiv.org)
	1 point by kawera 231 days ago \| hide \| past \| pdf \| discuss
1548.	Towards Autonomous Mathematics Research (arxiv.org)
	107 points by gmays 232 days ago \| hide \| past \| pdf \| 53 comments
1549.	Retrieval-Aware Distillation for Transformer-SSM Hybrids (arxiv.org)
	2 points by readitalready 232 days ago \| hide \| past \| pdf \| discuss
1550.	Biases in the Blind Spot: Detecting What LLMs Fail to Mention (arxiv.org)
	2 points by mpweiher 233 days ago \| hide \| past \| pdf \| discuss
1551.	Towards Autonomous Mathematics Research (Google DeepMind) (arxiv.org)
	1 point by u1hcw9nx 233 days ago \| hide \| past \| pdf \| discuss
1552.	Remote Labor Index: Measuring AI Automation of Remote Work (arxiv.org)
	2 points by Leynos 233 days ago \| hide \| past \| pdf \| discuss
1553.	Generalized on-policy distillation with reward extrapolation (arxiv.org)
	3 points by fzliu 233 days ago \| hide \| past \| pdf \| discuss
1554.	Adversarial Patch: images that make classifiers ignore other items in a scene (arxiv.org)
	1 point by felineflock 234 days ago \| hide \| past \| pdf \| discuss
1555.	Standardized and In-Depth Benchmarking of Post-Moore Dataflow AI Accelerators (arxiv.org)
	1 point by PaulHoule 234 days ago \| hide \| past \| pdf \| discuss
1556.	Fine-Tuning GPT-5 for GPU Kernel Generation (arxiv.org)
	4 points by matt_d 234 days ago \| hide \| past \| pdf \| discuss
1557.	SWE-ContextBench: context learning benchmark in coding (arxiv.org)
	1 point by mustaphah 234 days ago \| hide \| past \| pdf \| discuss
1558.	LLMs exceed physicians on complex text-based differential diagnosis (arxiv.org)
	3 points by rippeltippel 234 days ago \| hide \| past \| pdf \| 2 comments
1559.	Learning to Reason in 13 Parameters (arxiv.org)
	2 points by stared 234 days ago \| hide \| past \| pdf \| discuss
1560.	LLM Reasoning Failures (arxiv.org)
	1 point by gradus_ad 234 days ago \| hide \| past \| pdf \| discuss
	More