Large language models (LLMs) demonstrate strong individual task performance, yet still struggle to collaborate with users over extended, multi-turn interactions, for example by attempting solutions before understanding the user's needs or by failing to revise mistaken assumptions after receiving feedback. We propose Co...
Fanzhi Zeng, Anubrata Das, Maytal Saar-Tsechansky et al.· 0 citations
On-Policy Self-distillation is a self-improvement paradigm that enables large language models (LLMs) to improve their capabilities by leveraging the same model as both teacher and student under different conditioning contexts. However, we find that OPSD methods can progressively degrade previously acquired capabilities...
Despite extensive research, computational creativity still lacks a conceptually grounded, practically relevant, and empirically applicable formal definition across contexts such as art, scientific research, and games. Existing approaches to creativity often focus on proposing informal conceptual definitions without pro...
Neural networks routinely develop representations in which individual neurons contribute to multiple distinct functions, leading to the widespread view that such networks lack modular organization. We challenge this conclusion by introducing a formally nested hierarchy of modularity: unit-level, which requires distinct...
Shreya Saha, Benjamin K. Bergen, Meenakshi Khosla· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Multi-agent systems are increasingly used to solve coding tasks by coordinating agents that share code and plans. These agents are often optimized with reinforcement learning (RL) using automated evaluators, but bypassing evaluation can earn reward without producing a genuine solution. Prior work has largely treated re...
Yue-Peng Hu, P. Ghahremani, Reza Aghajani et al.· 0 citations
VEPA is introduced, a framework for the verified evolution of formal agent guardrails that represents the guardrail as a formal policy of executable symbolic rules over typed agent events and consistently outperforms baselines while expanding the scope of deterministic formal-policy enforcement.
Duy Nguyen, Lesly Miculicich, Bhavana Dalvi et al.· 0 citations
Self-evolving LLM agents typically improve how they act through accumulated experience, reflection, or skills. Yet even procedurally capable agents can fail when their beliefs about environment dynamics are incomplete, incorrect, or outdated. We study a complementary axis of self-evolution: evolving those beliefs durin...
Janet Wang, Jiang Guo, Yi Xiang et al.· 0 citations
Aligning two independently pretrained unimodal encoders typically demands millions of paired examples. In this paper, we study the regime where only $N \sim 100$--$500$ pairs are available, while unpaired data on either side is abundant. Our method expresses every representation by its similarities to the $N$ paired an...
Hardware datasheets contain engineering specifications essential for component selection, system integration, and hardware compatibility verification. However, manual inspection is tedious and error-prone because datasheets are lengthy and heterogeneous, with dense information fragmented across tables, figures, and tex...
Data-centric scaling of RLVR has focused on collecting or generating verifiable training problems. However, corpus size alone does not determine whether the dataset provides a useful learning signal for a target policy. To guide the synthesis of effective RLVR data, we experimentally characterize dataset effectiveness...
Ximing Lu, Aviral Kumar, Jan Kautz et al.· 0 citations
LLM agents can execute increasingly complex tasks, but effective assistance also requires aligning their actions with goals and constraints that users may leave unstated. We study this problem as interactive intent alignment through clarification. Yet clarification is useful only when the agent can turn the answer into...
Jiatan Huang, Zheyuan Zhang, Ziming Li et al.· 0 citations
Reinforcement learning with verifiable rewards (RLVR) provides reliable supervision for software engineering agents through executable tests, but binary rewards fail to distinguish trajectories with substantially different debugging quality. We investigate whether the current policy can judge its own trajectories and u...
Yi-Ran Wu, Andrew Zhao, Yu-Rui Chang et al.· 0 citations
