This study explores how different components of a coding harness affect the performance of autonomous coding agents. By varying planning, action space, and context management while keeping the execution loop fixed, the research evaluates 176 settings across four models on specific benchmarks. Key findings include the growing importance of context management with tighter context windows and the role of planning in cost efficiency for stronger models.
The chart will appear after repeat observations. The current metric comes from the source.
1 source votesReal observations only. History before source connection is not reconstructed.
This research provides insights into optimizing coding agents by analyzing the impact of specific harness components, which can guide the development of more efficient and effective coding systems.
The paper introduces XConf, a method for estimating confidence in language models by leveraging the model's accumulated experience. XConf uses past episodes, including tasks, reflections, confidence levels, outcomes, and lessons learned, to inform current confidence estimates through a recall and reflect process. It outperforms existing methods in discrimination and calibration with lower computational cost.
3 days agoDaily PapersLimiX-2 is a new model in the LimiX family that uses the Contextual Mechanism Networks (CMNs) paradigm, pretrained with Context-Conditional Masked Modeling (CCMM). It focuses on learning joint representations of data generation processes rather than target-centric prediction, showing superior performance on tabular data benchmarks and promoting causal awareness.
3 days agoDaily PapersStepAudio 3 Realtime is an audio-language foundation model designed for real-time spoken interaction, featuring a continuous listen-converse-think-act loop. It includes Deep Perception for interpreting user intent, Seamless Duplex for handling audio stream synchronization, and Think-While-Speaking to balance reasoning and latency. The model achieves high performance on benchmarks like MMSU and Artificial Analysis Full-Duplex, along with a task-success rate on τ-Voice.
6 days agoDaily PapersPhysBrain 1.5 is a unified model for understanding physical environments, generating actions, and predicting future states. It uses a vision-language foundation, encodes language responses and motion as sequences, and is pre-trained on human interaction videos. The model achieves strong performance on embodied understanding benchmarks.
4 days agoDaily PapersLynnReal-Omni is a native multimodal video generation framework that combines text-to-video, image-conditioned generation, and structural control into a single model. It includes a 32B shared multimodal diffusion transformer and a 27B Flash version for real-time rendering, with a data pipeline and evaluation method designed for video generation tasks.
4 days agoHacker NewsA 4B model was trained to generate query plans that are 81% faster than those produced by Postgres.
yesterday