30
42
30
30
55
COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization
COBRA-Skills uses contextual bandits to guide LLM agent skill evolution, cutting optimization cost 55-58% versus SkillOpt while topping six agent benchmarks.
COBRA-Skills formulates LLM agent skill optimization as budgeted sequential optimization over a dynamically evolving candidate space. It couples contextual-bandit-guided prioritization with evidence-grounded skill evolution, selectively spending execution-based evaluations on promising candidates while refining skills from feedback. Across six heterogeneous agent benchmarks and three target models, it achieves the strongest average performance while reducing optimization cost by 55-58% relative to SkillOpt using only 50 unique optimization examples per benchmark. The method remains robust to agent harness changes and works when the target model generates its own skills.
30
30
30
30
Online Learning with LLM Experts from Limited Feedback
Paper proposes bandit algorithms for adaptively routing prompts to LLM experts, minimizing regret under limited feedback budgets.
The paper formulates adaptive prompt routing to K LLM experts as a contextual bandit problem with d prompt features over T rounds. Proposed algorithms strategically select actions and observe rewards, achieving O(dT/m) regret in the full-information setting and O(dTK/m) in the bandit setting, where m is the feedback budget. Experiments demonstrate efficient learning of high-quality routing strategies across diverse LLMs from limited feedback.
25
45
A positive resolution of the gap-entropy conjecture
New proof resolves the gap-entropy conjecture for Gaussian bandits, bounding optimal best-arm identification samples by H(log(1/delta)+Ent(I)) up to constants.
A paper proves the gap-entropy conjecture for fixed-confidence best-arm identification with independent unit-variance Gaussian arms, means in [0,1], and a unique optimal arm. It shows the optimal expected sample count, averaged over arm-label permutations, is within absolute constant factors of H(log(1/delta)+Ent(I)), where H sums squared gaps and Ent(I) is the instance's gap-entropy. It also gives an instance-independent algorithm bounded by a constant multiple of this quantity plus a g^-2 loglog(e^e/g) term for the smallest gap g.
15
30
30
60
Five Venezuelan Nationals Plead Guilty in Kansas ATM Jackpotting Attempt
Five Venezuelan nationals pleaded guilty to failed ATM jackpotting attempts in Kansas as the FBI reports 700+ US incidents in 2025.
The five defendants traveled from Indiana to Kansas in December 2025 and tried to install malware on ATMs in Wamego and Manhattan, planning to remotely trigger the machines to dispense cash. Both attempts failed — one triggered an alarm — and the men were arrested days later after surveillance captured the thefts. All five pleaded guilty to conspiracy to commit bank larceny; one has received a nine-month prison sentence. The FBI counted more than 700 jackpotting incidents in 2025 with over $20 million in losses, part of 1,900 incidents since 2020.
40
Five plead guilty in latest federal ATM jackpotting case
Five Venezuelan nationals pleaded guilty to ATM jackpotting conspiracy tied to Ploutus malware, as FBI tallies $58 million in losses since 2021.
Five Venezuelan nationals pleaded guilty in Kansas federal court to conspiracy to commit bank larceny for attempted ATM jackpotting attacks in Wamego and Manhattan in December 2025; Luis Velasquez-Artigas was sentenced to nine months. The FBI says jackpotting has caused over $58 million in losses since 2021, with more than 1,900 incidents tracked since 2020 and over 700 in 2025. Separately, Juan Manuel Gouveia-Aguilera was sentenced to eight years and ordered to pay restitution for using Ploutus malware to steal more than $3.5 million from hundreds of ATMs. Prosecutors link the schemes to the Venezuelan gang Tren de Aragua and say at least 119 people have been charged.
35
42
30
57
60
60
42
30
42
60
57
57
30
30
30
30
55
30
42
30
30
45
57