New Links | ML News

ML Newsnew | past | best | rss | submit

931.	Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction (arxiv.org)
	57 points by root-parent 130 days ago \| hide \| past \| pdf \| 9 comments
932.	Spreadsheet-RL: Advancing LLM Agents on Realistic Spreadsheet Tasks (arxiv.org)
	3 points by ankitg12 130 days ago \| hide \| past \| pdf \| discuss
933.	Stateful Inference for Low-Latency Multi-Agent Tool Calling (arxiv.org)
	2 points by logotype 130 days ago \| hide \| past \| pdf \| 1 comment
934.	All of human cooking compressed into 2 megabytes (arxiv.org)
	444 points by josefchen 130 days ago \| hide \| past \| pdf \| 174 comments
935.	Tool-schema compression enables agentic RAG under constrained context budgets (arxiv.org)
	2 points by Sakizli 130 days ago \| hide \| past \| pdf \| 1 comment
936.	How sure is the activation oracle? (arxiv.org)
	1 point by evilscript 130 days ago \| hide \| past \| pdf \| discuss
937.	Advancing Mathematics Research with AI-Driven Formal Proof Search (arxiv.org)
	1 point by mrkn1 130 days ago \| hide \| past \| pdf \| discuss
938.	FML-Bench: A Controlled Study of AI Research Agent Strategies (arxiv.org)
	1 point by matt_d 130 days ago \| hide \| past \| pdf \| discuss
939.	Barriers to Complexity-Theoretic Proofs That "AGI" Using ML Is Impossible (arxiv.org)
	4 points by mike_uoftdcs 131 days ago \| hide \| past \| pdf \| discuss
940.	Agentic Harness Engineering (arxiv.org)
	3 points by cobblr_mosaic 131 days ago \| hide \| past \| pdf \| discuss
941.	SkillOpt: Executive Strategy for Self-Evolving Agent Skills (arxiv.org)
	4 points by theaniketmaurya 131 days ago \| hide \| past \| pdf \| discuss
942.	Polar: Agentic RL on Any Harness at Scale (arxiv.org)
	3 points by Brajeshwar 131 days ago \| hide \| past \| pdf \| discuss
943.	A sleep-like consolidation mechanism for LLMs (arxiv.org)
	212 points by juxtapose 131 days ago \| hide \| past \| pdf \| 140 comments
944.	Quest: Training Frontier Deep Research Agents with Synthetic Tasks (arxiv.org)
	2 points by Brajeshwar 131 days ago \| hide \| past \| pdf \| discuss
945.	Investigating how prompt politeness affects LLM accuracy (2025) (arxiv.org)
	156 points by KnuthIsGod 131 days ago \| hide \| past \| pdf \| 208 comments
946.	Contrastive Decoding Diffing: Recovering Finetuning Data Without Weight Access (arxiv.org)
	2 points by Timofeibu 131 days ago \| hide \| past \| pdf \| discuss
947.	ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention (arxiv.org)
	4 points by joesharratt29 131 days ago \| hide \| past \| pdf \| 1 comment
948.	Continual Speaker Identity Unlearning with Minimal Interference (arxiv.org)
	2 points by berlianta 131 days ago \| hide \| past \| pdf \| discuss
949.	MileStone: A Multi-Objective Compiler Phase Ordering Framework (arxiv.org)
	1 point by matt_d 131 days ago \| hide \| past \| pdf \| discuss
950.	LLMs require curated context for reliable political fact-checking (arxiv.org)
	3 points by teleforce 132 days ago \| hide \| past \| pdf \| discuss
951.	Advancing mathematics research with AI-driven formal proof search (arxiv.org)
	2 points by azhenley 132 days ago \| hide \| past \| pdf \| discuss
952.	Evaluating Large Language Models in a Complex Hidden Role Game (arxiv.org)
	1 point by Brajeshwar 132 days ago \| hide \| past \| pdf \| discuss
953.	SkillOpt: Executive Strategy for Self-Evolving Agent Skills (arxiv.org)
	4 points by simonpure 132 days ago \| hide \| past \| pdf \| discuss
954.	A Language for Describing Agentic LLM Contexts (arxiv.org)
	4 points by mpweiher 133 days ago \| hide \| past \| pdf \| discuss
955.	Advancing Mathematics Research with AI-Driven Formal Proof Search (arxiv.org)
	3 points by tamnd 133 days ago \| hide \| past \| pdf \| discuss
956.	Constraint Decay: The Fragility of LLM Agents in Back End Code Generation (arxiv.org)
	287 points by wek 133 days ago \| hide \| past \| pdf \| 197 comments
957.	SSV: Sparse Speculative Verification for Efficient LLM Inference (arxiv.org)
	4 points by matt_d 133 days ago \| hide \| past \| pdf \| discuss
958.	Characterizing Real-World Bugs in Tile Programs for Automated Bug Detection (arxiv.org)
	2 points by matt_d 134 days ago \| hide \| past \| pdf \| discuss
959.	Customizing an LLM for Enterprise Software Engineering (arxiv.org)
	4 points by daureg 134 days ago \| hide \| past \| pdf \| discuss
960.	Agentic Compilation: Reducing LLM Rerun Costs (arxiv.org)
	3 points by rebekkamikkoa 134 days ago \| hide \| past \| pdf \| discuss
	More