Linguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware Unlearning

PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents

On-policy distillation (OPD) is a promising approach for training language agents, providing dense teacher supervision on student-generated trajectories.

9h ago ·arxiv.org

cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents

Computer use agents (CUAs), which use graphical user interfaces (GUIs) to complete tasks on a computer, have recently surpassed human performance on many standard benchmarks, including difficult…

9h ago ·arxiv.org

What happens when an LLM loop runs away: the guardrail pattern

Nobody budgets for the runaway loop. Every AI SaaS has a line item for "expected LLM spend" and nobody has a line item for "the Friday night a bug turned our agent into a money printer." I've seen the…

• Implement guardrail pattern to prevent runaway LLM loops
• Price every call using pricing table per model
• Maintain pre-aggregated spend ledger for fast cost checks

9h ago ·dev.to

CAS II: Symmetric Partitions as Kolmogorov Models

In algorithmic statistics a string x is explained by a finite set containing it, and Kolmogorov's structure function records the smallest such model at each level of complexity.

9h ago ·arxiv.org