29 citations · 39 across the 22 of their papers we have counts for
26 papers
TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents
Aaron J. Li, Weijia Xu, Chandan Singh +8
Advances in frontier coding agents have sharply increased the token costs of AI-assisted software engineering. Their token efficiency is typically evaluated on isolated tasks, wher…
DuoDiscover: Scaling Autonomous Discovery Beyond the Evaluation Bottleneck
Shubham Agarwal, Akshat Gupta, Mike Heddes +21
Evaluation has been central to advances in AI, and it is equally critical to autonomous discovery. Yet scaling autonomous discovery to real-world engineering challenges faces a fun…
Pincer: Resource Authorization for Agents using a Digital Twin
Mayank Rathee, Alexander Stepanov, Shalin Madabhavi +3
Coding agents have become increasingly long-horizon, autonomous, reliant on general-purpose shell and maintain their own persistent memory for self-improvement. While these capabil…
Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering
Alexander Krentsel, Shubham Agarwal, Mert Cemri +5
Software development follows an implementation-verification loop in which developers or agents iteratively revise an implementation until an evaluator, such as a test suite, accept…
Fantastic Adaptive Taxonomies and How to Use Them
Mert Cemri, Andrei Cojocaru, Melissa Pan +9
An agent system's execution traces record how it fails, and procedures that improve such a system without changing model weights (trajectory selection, prompt and workflow optimiza…
LLM-as-a-Verifier: A General-Purpose Verification Framework
Jacky Kwok, Shulu Li, Pranav Atreya +6
Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we identify verification, the abi…
DualEval: Joint Model-Item Calibration for Unified LLM Evaluation
Aaron J. Li, Hao Huang, Youngmin Park +6
Current LLM evaluation relies on two complementary but often disconnected signals: static benchmarks with objective correctness labels and arena-style preference data that better r…
Playful Agentic Robot Learning
Junyi Zhang, Jiaxin Ge, Hanjun Yoo +17
Current agentic robot systems can write executable Code-as-Policy programs, observe feedback, and revise behavior across multiple attempts, but they remain largely task-driven: reu…
BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution
Yangzhen Wu, Aaron J. Li, Wenjie Ma +10
The rapid progress of frontier large language models has led to widespread benchmark saturation, limiting the ability of existing datasets to differentiate model capabilities or pr…
Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI
Tian Xia, Hanchen Li, Zhifei Li +5
Modern LLM serving systems increasingly host agentic workloads, whose sessions issue tens of model invocations interleaved with tool calls, accumulating KV cache that can be reused…
Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
Shubham Agarwal, Alexander Krentsel, Shu Liu +10
AI agents increasingly excel at generating, testing, and refining code. However, they fall short on tasks requiring formal guarantees of full coverage that testing alone cannot pro…
optimize_anything: A Universal API for Optimizing any Text Parameter
Lakshya A Agrawal, Donghyun Lee, Shangyin Tan +11
Can a single LLM-based optimization system match specialized tools across fundamentally different domains? We show that when optimization problems are formulated as improving a tex…
AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
Haizhong Zheng, Yizhuo Di, Jiahui Wang +7
Reinforcement learning (RL) is increasingly used to improve the reasoning, coding, and tool-use capabilities of large language models, but agentic RL remains prohibitively expensiv…
Combee: Scaling Prompt Learning for Self-Improving Language Model Agents
Hanchen Li, Runyuan He, Qizheng Zhang +11
Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without parameter changes. For example, existing…
ClawEnvKit: Automatic Environment Generation for Claw-Like Agents
Xirui Li, Ming Li, Ion Stoica +2
Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that what is needed is not just a dat…
EvoX: Meta-Evolution for Automated Discovery
Shu Liu, Shubham Agarwal, Monishwaran Maheswaran +14
Recent work such as AlphaEvolve has shown that combining LLM-driven optimization with evolutionary search can effectively improve programs, prompts, and algorithms across domains.…
The Price Reversal Phenomenon: When Cheaper Reasoning Models Cost More
Lingjiao Chen, Chi Zhang, Yeye He +3
Developers and consumers increasingly choose reasoning models (RMs) based on their listed API prices. However, how accurately do these prices reflect actual inference costs? We con…
K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model
Shiyi Cao, Ziming Mao, Joseph E. Gonzalez +1
Optimizing GPU kernels is critical for efficient modern machine learning systems yet remains challenging due to the complex interplay of design factors and rapid hardware evolution…
AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
Mert Cemri, Shubham Agrawal, Akshat Gupta +9
The paradigm of automated program generation is shifting from one-shot generation to inference-time search, where Large Language Models (LLMs) function as semantic mutation operato…
Measuring Agents in Production
Melissa Z. Pan, Negar Arabzadeh, Riccardo Cogo +22
LLM-based agents already operate in production across many industries, yet we lack an understanding of what technical methods make deployments successful. We present the first syst…
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Lakshya A Agrawal, Shangyin Tan, Dilara Soylu +14
Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often requir…
GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents
Manish Shetty, Naman Jain, Jinjian Liu +3
Developing high-performance software is a complex task that requires specialized expertise. We introduce GSO, a benchmark for evaluating language models' capabilities in developing…
R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
Naman Jain, Jaskirat Singh, Manish Shetty +3
Improving open-source models on real-world SWE tasks (solving GITHUB issues) faces two key challenges: 1) scalable curation of execution environments to train these models, and, 2)…
GoEX: Perspectives and Designs Towards a Runtime for Autonomous LLM Applications
Shishir G. Patil, Tianjun Zhang, Vivian Fang +7
Large Language Models (LLMs) are evolving beyond their classical role of providing information within dialogue systems to actively engaging with tools and performing actions on rea…