New Links | ML News

ML Newsnew | past | best | rss | submit

1411.	Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory (arxiv.org)
	2 points by simonpure 213 days ago \| hide \| past \| pdf \| discuss
1412.	Asymmetric Goal Drift in Coding Agents Under Value Conflict (arxiv.org)
	1 point by lrakster 213 days ago \| hide \| past \| pdf \| discuss
1413.	Agentic Code Reasoning (arxiv.org)
	3 points by gmays 213 days ago \| hide \| past \| pdf \| discuss
1414.	General Agentic Memory via Deep Research (arxiv.org)
	2 points by gmays 214 days ago \| hide \| past \| pdf \| discuss
1415.	A Dual-LLM Policy for Reducing Noise in Agentic Program Repair (arxiv.org)
	1 point by azhenley 214 days ago \| hide \| past \| pdf \| discuss
1416.	Actor-Curator: Learning the Training Curriculum for RL Post-Training (arxiv.org)
	2 points by jonathanlight 214 days ago \| hide \| past \| pdf \| 1 comment
1417.	Evaluating Theory of Mind and Internal Beliefs in LLM-Based Multi-Agent Systems (arxiv.org)
	1 point by Anon84 215 days ago \| hide \| past \| pdf \| discuss
1418.	DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference (arxiv.org)
	2 points by nsoonhui 215 days ago \| hide \| past \| pdf \| 1 comment
1419.	CuTe Layout Representation and Algebra (arxiv.org)
	4 points by matt_d 215 days ago \| hide \| past \| pdf \| discuss
1420.	Speculative Speculative Decoding (SSD) (arxiv.org)
	61 points by E-Reverance 215 days ago \| hide \| past \| pdf \| 9 comments
1421.	How Well Does Agent Development Reflect Real-World Work? (arxiv.org)
	3 points by salkahfi 215 days ago \| hide \| past \| pdf \| discuss
1422.	130k Lines of Formal Topology: Simple and Cheap Autoformalization for Everyone? (arxiv.org)
	34 points by PaulHoule 215 days ago \| hide \| past \| pdf \| 11 comments
1423.	Learning-Based Multi-Stage Strategy for Aircraft to Evade Missile (arxiv.org)
	1 point by rbanffy 215 days ago \| hide \| past \| pdf \| discuss
1424.	LeRobot: An Open-Source Library for End-to-End Robot Learning (arxiv.org)
	2 points by nill0 216 days ago \| hide \| past \| pdf \| discuss
1425.	CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation (arxiv.org)
	3 points by petethomas 216 days ago \| hide \| past \| pdf \| discuss
1426.	Run your agent 10 times – you won't get the same answer (arxiv.org)
	5 points by amanmehta1997 216 days ago \| hide \| past \| pdf \| 1 comment
1427.	Language Model Contains Personality Subnetworks (arxiv.org)
	58 points by PaulHoule 216 days ago \| hide \| past \| pdf \| 34 comments
1428.	Toward Guarantees for Clinical Reasoning in Vision Language Models (arxiv.org)
	2 points by tinarchitect 217 days ago \| hide \| past \| pdf \| discuss
1429.	Toward Guarantees for Clinical Reasoning in Vision Language Models (arxiv.org)
	5 points by barthelomew 217 days ago \| hide \| past \| pdf \| 3 comments
1430.	FlyTrap: Attract autonomous drones with an adversarial umbrella (arxiv.org)
	2 points by fainpul 217 days ago \| hide \| past \| pdf \| 1 comment
1431.	GPT detectors are biased against non-native English writers (2023) (arxiv.org)
	2 points by maxloh 218 days ago \| hide \| past \| pdf \| discuss
1432.	Latent-Space Communication in Heterogeneous Multi-Agent Systems (arxiv.org)
	7 points by ekaesmem 218 days ago \| hide \| past \| pdf \| 1 comment
1433.	A Reinforcement Learning Environment for Automatic Code Optimization in MLIR (arxiv.org)
	1 point by matt_d 218 days ago \| hide \| past \| pdf \| discuss
1434.	Frontier AI Models Exhibit Sophisticated Reasoning in Simulated Nuclear Crises (arxiv.org)
	3 points by iamskeole 218 days ago \| hide \| past \| pdf \| discuss
1435.	Doc-to-LoRA: Learning to Instantly Internalize Contexts (arxiv.org)
	1 point by rbanffy 218 days ago \| hide \| past \| pdf \| discuss
1436.	Agents of Chaos (arxiv.org)
	4 points by ukuina 218 days ago \| hide \| past \| pdf \| 1 comment
1437.	Kimi K2: Open Agentic Intelligence (arxiv.org)
	2 points by Anon84 219 days ago \| hide \| past \| pdf \| discuss
1438.	Prompt Repetition Improves Non-Reasoning LLMs (arxiv.org)
	1 point by tosh 219 days ago \| hide \| past \| pdf \| discuss
1439.	Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use (arxiv.org)
	2 points by Anon84 219 days ago \| hide \| past \| pdf \| discuss
1440.	Deep Learning: Our Year 1990-1991 (arxiv.org)
	1 point by vinhnx 219 days ago \| hide \| past \| pdf \| discuss
	More