works on

From the 1 of 8 linked papers with an AI index.

collaborators

8 papers

cs.AI2026

Probing the Origins of Reasoning Performance: Representational Quality for Mathematical Problem-Solving in RL vs. SFT Fine-Tuned Models

Antyabha Rahman, Akshaj Gurugubelli, Omar Ankit +2

The paper investigates why reinforcement‑learning‑trained models outperform supervised fine‑tuned models on math reasoning by analyzing their internal representations with linear p…

cs.AI2026

Interpreting Latent CoT Reasoning as Dynamical Systems

Sabari Iyyappan Duraipandian, Shreya Sanjay Boyane, Manju Nagesh +3

Recent latent reasoning methods, such as CODI and COCONUT, face a fundamental interpretability problem: they maintain multiple superimposed candidate traces in the hidden space at…

cs.MA2026

From Competition to Coordination: Market Making as a Scalable Framework for Safe and Aligned Multi-Agent LLM Systems

Brendan Gho, Suman Muppavarapu, Afnan Shaik +6

As foundation models are increasingly deployed as interacting agents in multi-agent systems, their collective behavior raises new challenges for trustworthiness, transparency, and…

cs.LG2026

Mitigating Forgetting in Continual Learning with Selective Gradient Projection

Anika Singh, Aayush Dhaulakhandi, Varun Chopade +3

As neural networks are increasingly deployed in dynamic environments, they face the challenge of catastrophic forgetting, the tendency to overwrite previously learned knowledge whe…

cs.CL2025

Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness

Lang Xiong, Nishant Bhargava, Jianhang Hong +4

Large Language Models (LLMs) often exhibit significant behavioral shifts when they perceive a change from a real-world deployment context to a controlled evaluation setting, a phen…

cs.LG2025

Peek-a-Boo Reasoning: Contrastive Region Masking in MLLMs

Isha Chaturvedi, Anjana Nair, Yushen Li +5

We introduce Contrastive Region Masking (CRM), a training free diagnostic that reveals how multimodal large language models (MLLMs) depend on specific visual regions at each step o…