70 citations · 161 across the 37 of their papers we have counts for
11 papers · 1 filter
Rethinking Successive Rejects Algorithms
Mohamed Khair, Junpei Komiyama
In the best-arm identification problem, an algorithm adaptively selects arms to find the arm of the largest mean reward. Successive Rejects (SR) is a simple fixed-budget best-arm i…
Self-Adapting Group of Experts for Multi-Agent Reasoning
Mohammad Atif Quamar, Nurbek Tastan, Karthik Nandakumar +1
Multi-agent systems bring together language model agents with different roles to propose, review, and refine solutions. Each agent's response depends on its model's capabilities, t…
Prefix-Denoising Consistency: Test-Time Verification for Diffusion Language Models
Yuki Ichihara, Naoto Iwase, Mohammad Atif Quamar +1
Diffusion Language Models (DLMs) have recently become increasingly competitive with autoregressive (AR) models, and even outperform them on certain tasks. Unlike AR models, DLMs pr…
SGHA: Evidence-Grounded Research Problem Discovery with Local Language Models
Sarvesh Gharat, Junpei Komiyama
Recent efforts toward fully automated AI scientists have demonstrated that language-model agents can generate hypotheses, execute experiments, and draft scientific manuscripts. How…
Learning Optimal Dynamic Matching via Graph Neural Networks
Genta Okada, Shunya Noda, Junpei Komiyama +1
Dynamic matching markets require decisions about whom to match and when: matching now yields value but removes participants who may create better future opportunities. We develop a…
Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation
Yuki Ichihara, Naoto Iwase, Mohammad Atif Quamar +1
On-Policy Self-Distillation (OPSD) is commonly interpreted as the transfer of privileged information: a teacher observes the verified solution to the target problem and supervises…
Fixed-Confidence Best-Arm Identification for Causal Mediation Analysis
Harsh Shrivastava, Yuta Kawakami, Junpei Komiyama +1
This paper studies the problem of identifying the treatment that maximizes the expected natural direct potential outcome (NDPO), which captures the potential outcome of an interven…
Regret Analysis of Retry-Based Bandits
Bingkui Tong, Junpei Komiyama, Soichiro Nishimori +1
We provide the first regret analysis of ReMax in stochastic multi-armed bandits. Originally introduced for reinforcement learning, ReMax is motivated by the role of exploration whe…
Reliable Chain-of-Thought via Prefix Consistency
Naoto Iwase, Yuki Ichihara, Mohammad Atif Quamar +1
Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority voting (MV), a test-time techn…
CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency
Hirofumi Ota, Naoto Iwase, Yuki Ichihara +2
Large language models often improve reasoning by sampling multiple outputs and aggregating their final answers, but precise and efficient control of error levels remains a challeng…
An Efficient Algorithm for Thresholding Monte Carlo Tree Search
Shoma Nameki, Atsuyoshi Nakamura, Junpei Komiyama +1
We introduce the Thresholding Monte Carlo Tree Search problem, in which, given a tree and a threshold , a player must answer whether the root node value of $\mathc…