5 citations · 15 across the 25 of their papers we have counts for
28 papers
A History-Aware Visually Grounded Critic for Computer Use Agents
Jaewoo Lee, Zaid Khan, Archiki Prasad +7
Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-execution action evaluation in compl…
AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
Duy Nguyen, Hanqi Xiao, Archiki Prasad +7
Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the teacher being conditioned on…
Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty
Joykirat Singh, Zaid Khan, Archiki Prasad +5
Large language models (LLMs) are increasingly deployed on long-horizon tasks in partially observable environments, where they must act while inferring and tracking a complex enviro…
Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems
Justin Chih-Yao Chen, Archiki Prasad, Zaid Khan +4
Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning abilities of LLMs, yet a fundamental limitation remains: models cannot learn from problems that are…
Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates
Duy Nguyen, Hanqi Xiao, Archiki Prasad +3
Large language models (LLMs) rely on internal knowledge to solve many downstream tasks, making it crucial to keep them up to date. Since full retraining is expensive, prior work ha…
Effective Reasoning Chains Reduce Intrinsic Dimensionality
Archiki Prasad, Mandar Joshi, Kenton Lee +2
Chain-of-thought (CoT) reasoning and its variants have substantially improved the performance of language models on complex reasoning tasks, yet the precise mechanisms by which dif…
PRInTS: Reward Modeling for Long-Horizon Information Seeking
Jaewoo Lee, Archiki Prasad, Justin Chih-Yao Chen +3
Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step infor…
Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression
Joykirat Singh, Justin Chih-Yao Chen, Archiki Prasad +3
Recent thinking models are capable of solving complex reasoning tasks by scaling test-time compute, but this scaling should be allocated in line with task difficulty. On one hand,…
One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
Zaid Khan, Archiki Prasad, Elias Stengel-Eskin +2
Symbolic world modeling requires inferring and representing an environment's transitional dynamics as an executable program. Prior work has focused on largely deterministic environ…
GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs
Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin +1
Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at t…
Retrieval-Augmented Generation with Conflicting Evidence
Han Wang, Archiki Prasad, Elias Stengel-Eskin +1
Large language model (LLM) agents are increasingly employing retrieval-augmented generation (RAG) to improve the factuality of their responses. However, in practice, these systems…
Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems
Zaid Khan, Elias Stengel-Eskin, Archiki Prasad +2
Scientists often infer abstract procedures from specific instances of problems and use the abstractions to generate new, related instances. For example, programs encoding the forma…
Multi-Attribute Steering of Language Models via Targeted Intervention
Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin +1
Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.g., improving helpfulness) by inte…
Learning to Generate Unit Tests for Automated Debugging
Archiki Prasad, Elias Stengel-Eskin, Justin Chih-Yao Chen +2
Unit tests (UTs) play an instrumental role in assessing code correctness as well as providing feedback to large language models (LLMs), motivating automated test generation. Howeve…
Self-Consistency Preference Optimization
Archiki Prasad, Weizhe Yuan, Richard Yuanzhe Pang +6
Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area. However, existing techniques often fail to improve complex…
LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits
Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin +1
Reward Models (RMs) are crucial to aligning large language models (LLMs), but the degree to which an RM specialized to one task (e.g. writing) generalizes to new tasks (e.g. math)…
MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning
Justin Chih-Yao Chen, Archiki Prasad, Swarnadeep Saha +2
Large Language Models' (LLM) reasoning can be improved using test-time aggregation strategies, i.e., generating multiple samples and voting among generated samples. While these imp…
AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge
Han Wang, Archiki Prasad, Elias Stengel-Eskin +1
Knowledge conflict arises from discrepancies between information in the context of a large language model (LLM) and the knowledge stored in its parameters. This can hurt performanc…
System-1.x: Learning to Balance Fast and Slow Planning with Language Models
Swarnadeep Saha, Archiki Prasad, Justin Chih-Yao Chen +3
Language models can be used to solve long-horizon planning problems in two distinct modes: a fast 'System-1' mode, directly generating plans without any explicit search or backtrac…
Soft Self-Consistency Improves Language Model Agents
Han Wang, Archiki Prasad, Elias Stengel-Eskin +1
Generations from large language models (LLMs) can be improved by sampling and scoring multiple solutions to select a final answer. Current "sample and select" methods such as self-…
ReGAL: Refactoring Programs to Discover Generalizable Abstractions
Elias Stengel-Eskin, Archiki Prasad, Mohit Bansal
While large language models (LLMs) are increasingly being used for program synthesis, they lack the global view needed to develop useful abstractions; they generally predict progra…
ADaPT: As-Needed Decomposition and Planning with Language Models
Archiki Prasad, Alexander Koller, Mareike Hartmann +4
Large Language Models (LLMs) are increasingly being used for interactive decision-making tasks requiring planning and adapting to the environment. Recent works employ LLMs-as-agent…
Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal
An increasing number of vision-language tasks can be handled with little to no training, i.e., in a zero and few-shot manner, by marrying large language models (LLMs) to vision enc…
ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness
Archiki Prasad, Swarnadeep Saha, Xiang Zhou +1
Multi-step reasoning ability is fundamental to many natural language tasks, yet it is unclear what constitutes a good reasoning chain and how to evaluate them. Most existing method…