24 citations · 92 across the 63 of their papers we have counts for
64 papers
On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents
Aaron Wang, Neelabh Madan, Vlad Sobal +5
We study whether small LLM agents can operate effectively under explicit wall-clock time budgets by both respecting the allocated runtime and using available time productively. We…
StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns
Vlad Sobal, Shuo Yang, Yuting Zhang +2
We introduce StaminaBench, a benchmark that measures the stamina of coding agents: how many consecutive interaction turns (change requests) they can handle before failing. Unlike t…
DLLG: Dynamic Logit-Level Gating of LLM Experts
Bingnan Li, Zhaoyang Zhang, Xiaoze Liu +6
Leveraging multiple specialized LLMs can combine complementary strengths, but existing approaches trade adaptability for stability: routing commits prematurely, heuristic ensemblin…
Priming: Hybrid State Space Models From Pre-trained Transformers
Aditya Chattopadhyay, Elvis Nunez, Prannay Kaul +6
Hybrid State-Space models combine Attention with recurrent State-Space Model (SSM) layers, balancing eidetic memory from Attention with compressed fading memory from SSMs. This yie…
Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
Xiaoze Liu, Dhananjay Ram, Yuting Zhang +3
We introduce Mutual Reinforcement Learning, a framework for concurrent RL post-training in which heterogeneous LLM policies exchange typed experience while keeping separate paramet…
ExecTune: Effective Steering of Black-Box LLMs with Guide Models
Vijay Lingam, Aditya Golatkar, Anwesan Pal +6
For large language models deployed through black-box APIs, recurring inference costs often exceed one-time training costs. This motivates composed agentic systems that amortize exp…
Asymmetric Actor-Critic for Multi-turn LLM Agents
Shuli Jiang, Zhaoyang Zhang, Yi Zhang +3
Large language models (LLMs) exhibit strong reasoning and conversational abilities, but ensuring reliable behavior in multi-turn interactions remains challenging. In many real-worl…
Learning When to Attend: Conditional Memory Access for Long-Context LLMs
Sakshi Choudhary, Aditya Chattopadhyay, Luca Zancato +4
Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on long-context data can help but is…
Reinforcement-aware Knowledge Distillation for LLM Reasoning
Zhaoyang Zhang, Shuli Jiang, Yantao Shen +6
Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such model…
EvoMAS: Evolutionary Generation of Multi-Agent Systems
Yuntong Hu, Yuting Zhang, Matthew Trager +4
Large language model (LLM)-based multi-agent systems (MAS) show strong promise for complex reasoning, planning, and tool-augmented tasks, but designing effective MAS architectures…
Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes
Jing Tan, Zhaoyang Zhang, Yantao Shen +6
We introduce Talk2Move, a reinforcement learning (RL) based diffusion framework for text-instructed spatial transformation of objects within scenes. Spatially manipulating objects…
Experience-Guided Adaptation of Inference-Time Reasoning Strategies
Adam Stein, Matthew Trager, Benjamin Bowman +4
Enabling agentic AI systems to adapt their problem-solving approaches based on post-training interactions remains a fundamental challenge. While systems that update and maintain a…
e1: Learning Adaptive Control of Reasoning Effort
Michael Kleinman, Matthew Trager, Alessandro Achille +2
Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users may prefer to allocate different a…
Learning to Focus: Focal Attention for Selective and Scalable Transformers
Dhananjay Ram, Wei Xia, Stefano Soatto
Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces nois…
Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression
Liangzu Peng, Aditya Chattopadhyay, Luca Zancato +3
Linear State-Space Models (SSMs) offer an efficient alternative to softmax Attention with constant memory and linear compute, but their lossy, fading summary of the past hurts reca…
Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning
Renos Zabounidis, Aditya Golatkar, Michael Kleinman +3
We propose Re-FORC, an adaptive reward prediction method that, given a query, enables prediction of the expected future rewards as a function of the number of future thinking token…
AI Agents as Universal Task Solvers
Alessandro Achille, Stefano Soatto
We describe AI agents as stochastic dynamical systems and frame the problem of learning to reason as in transductive inference: Rather than approximating the distribution of past d…
LATTS: Locally Adaptive Test-Time Scaling
Theo Uscidda, Matthew Trager, Michael Kleinman +3
One common strategy for improving the performance of Large Language Models (LLMs) on downstream tasks involves using a \emph{verifier model} to either select the best answer from a…
Maximally-Informative Retrieval for State Space Model Generation
Evan Becker, Benjamin Bowman, Matthew Trager +4
Given a query and dataset, the optimal way of answering the query is to make use all the information available. Modern LLMs exhibit impressive ability to memorize training data, bu…
PICASO: Permutation-Invariant Context Composition with State Space Models
Tian Yu Liu, Alessandro Achille, Matthew Trager +3
Providing Large Language Models with relevant contextual knowledge at inference time has been shown to greatly improve the quality of their generations. This is often achieved by p…
Descriminative-Generative Custom Tokens for Vision-Language Models
Pramuditha Perera, Matthew Trager, Luca Zancato +2
This paper explores the possibility of learning custom tokens for representing new concepts in Vision-Language Models (VLMs). Our aim is to learn tokens that can be effective for b…
Expansion Span: Combining Fading Memory and Retrieval in Hybrid State Space Models
Elvis Nunez, Luca Zancato, Benjamin Bowman +3
The "state" of State Space Models (SSMs) represents their memory, which fades exponentially over an unbounded span. By contrast, Attention-based models have "eidetic" (i.e., verbat…
The N-Grammys: Accelerating Autoregressive Inference with Learning-Free Batched Speculation
Lawrence Stewart, Matthew Trager, Sujan Kumar Gonugondla +1
Speculative decoding aims to speed up autoregressive generation of a language model by verifying in parallel the tokens generated by a smaller draft model.In this work, we explore…
Conjuring Semantic Similarity
Tian Yu Liu, Stefano Soatto
The semantic similarity between sample expressions measures the distance between their latent 'meaning'. These meanings are themselves typically represented by textual expressions.…