Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression
Paper • 2510.01581 • Published • 2
Singh
joykirat
AI & ML interests
None yet
Organizations
None yet
authored 5
papers 3 months ago
Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use
Paper • 2603.03205 • Published • 13
Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems
Paper • 2604.04767 • Published • 7
Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty
Paper • 2605.11436 • Published • 1
MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
Paper • 2605.18565 • Published • 5
submitted a
paper to Daily Papers 3 months ago
submitted a
paper to Daily Papers 4 months ago
authored 4
papers over 1 year ago
Exposing the Achilles' Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning
Paper • 2406.10834 • Published
PromptWizard: Task-Aware Prompt Optimization Framework
Paper • 2405.18369 • Published • 1
Self-Evolved Preference Optimization for Enhancing Mathematical Reasoning in Small Language Models
Paper • 2503.04813 • Published • 2
Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning
Paper • 2505.01441 • Published • 40