17 papers
Effect of deep-trap density of states for a-Si:H layers on HIT cell performances: Modeling Framework
Tewfik Souier, Adel Gougam
In this work, an aSi and cSi heterojunction solar cell with an intrinsic layer is simulated using AFORS-HET software. The study focuses on the role of the electronic density of sta…
SWEeper-Bench: Can Agents Discover Bugs in Interactive Software?
Yang Yao, Haozhe Chen, Bingyi Kang +2
Coding agents increasingly interact with users by generating interactive software on the fly rather than replying in text, yet many bugs in such software reveal themselves only aft…
Up and Down the Abstraction Ladder: Code-Based Skills for Language Agents
Bartłomiej Cupiał, Jens Tuyls, Maciej Wołczyk +5
Language agents struggle to act and learn in environments that require long sequences of low-level actions. Code-based abstractions can make these agents more productive by letting…
-Multilingual: Benchmarking Voice Agents Across Languages
Soham Ray, Edgard dos Santos Paiva, Ruben Valenzuela +3
English-only benchmarks expose only a narrow slice of voice-agent behavior. We introduce -Multilingual, extending -Voice to Spanish, Brazilian Portuguese, Hindi, Korean, and…
-Bench: An Environment for End-To-End, Realistic Agent Construction
Quan Shi, Keshav Dhandhania, Karthik Narasimhan +1
LLM agents are rapidly becoming production software, deployed to handle customer service, adjudicate disputes, and operate internal systems. Notably, the work of building them is i…
-Rec: A Verifiable Benchmark for Agentic Recommender Systems
Bharath Sivaram Narasimhan, Karthik R Narasimhan
As recommender systems transition toward agentic, multi-turn conversational interfaces, evaluation paradigms have struggled to keep pace. Current benchmarks often rely on "LLM-as-a…
CEO-Bench: Can Agents Play the Long Game?
Haozhe Chen, Karthik Narasimhan, Zhuang Liu
Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and customer service. Yet real-world challenges require a comb…
Humans are Missing from AI Coding Agent Research
Zora Z. Wang, John Yang, Kilian Lieret +10
Recent progress in AI coding agent research has led to rapid improvements in agents' ability to autonomously perform complex software engineering tasks, from editing large codebase…
Context-Aware RL for Agentic and Multimodal LLMs
Peiyang Xu, Bangzheng Li, Sijia Liu +4
Large language models (LLMs) often fail when answering requires identifying a small but decisive piece of evidence within a long or complex context, such as a single line in a tool…
-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains
Soham Ray, Keshav Dhandhania, Victor Barres +1
Full-duplex voice agents--systems that listen and speak simultaneously--are rapidly moving from research to production. However, existing evaluations address conversational dynamic…
-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge
Quan Shi, Alexandra Zytek, Pedram Razavi +2
Conversational agents are increasingly deployed in knowledge-intensive settings, where correct behavior depends on retrieving and applying domain-specific knowledge from large, pro…
An Efficient Algorithm for Thresholding Monte Carlo Tree Search
Shoma Nameki, Atsuyoshi Nakamura, Junpei Komiyama +1
We introduce the Thresholding Monte Carlo Tree Search problem, in which, given a tree and a threshold , a player must answer whether the root node value of $\mathc…
SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar +1
The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for discovering vulnerabilities and ensuring…
Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
Howard Chen, Noam Razin, Karthik Narasimhan +1
Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In t…
BuilderBench: The Building Blocks of Intelligent Agents
Raj Ghugare, Roger Creus Castanyer, Catherine Ji +4
Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel…
When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration
Quan Shi, Carlos E. Jimenez, Shunyu Yao +3
Recent advancements in AI reasoning have driven substantial improvements across diverse tasks. A critical open question is whether these improvements also yields better knowledge t…
Contextual Experience Replay for Self-Improvement of Language Agents
Yitao Liu, Chenglei Si, Karthik Narasimhan +1
Large language model (LLM) agents have been applied to sequential decision-making tasks such as web navigation, but without any environment-specific experiences, they often fail in…