20 results for “task-conditioned”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper studies the design of context for self-distillation in language models, finding that step-aligned feedback yields the largest gains.
Xinyu Luo, Hui Liu, Yihua Shao, Junyi Yang +2 more
The paper proposes Conditional Retrieval Alignment (CoRA), a gradient-free framework for task-conditioned retrieval using a frozen encoder and paired inputs and outputs.
Sina Mavali, David Pape, Jonathan Evertz, Samira Abedini +4 more
The paper introduces the Task Alignment Benchmark (TAB) to evaluate terminal agents' ability to selectively follow relevant environmental instructions while ignoring misleading distractors, revealing…
Tomer Keren, Nitay Calderon, Asaf Yehudai, Yotam Perlitz +2 more
The paper introduces TASTE, an automatic task synthesis method that generates challenging agent benchmarks by evolving tool sequences, demonstrating that existing benchmarks are saturated and that TAS…
This paper argues that large language models have fundamental limitations as general-purpose solvers due to the capacity-limited nature of language as a communication channel and alignment constraints…
Zechu Li, Yufeng Jin, Puze Liu, Jan Peters +1 more
This paper proposes a systematic RL-based data generation pipeline for dexterous bimanual manipulation.
Siyi Gu, Jialin Chen, Sophia Zhou, Arman Cohan +1 more
The paper proposes a framework for post-training of reasoning language models using rubrics as structured feedback for self-distillation.
This paper introduces a task-oriented randomization methodology to stabilize black-box models while leveraging prior information.
This paper develops a policy-learning framework to optimally assign prediction tasks to multiple agents, considering individual agent expertise and capacity constraints, achieving systematic performan…
Dihong Huang, Zhenyu Wei, Zhuxiu Xu, Yunchao Yao +2 more
A framework called DexCompose is proposed to reuse pretrained dexterous policies for multi-task manipulation with explicit finger-level action ownership.
Youngwon Choi, Hyeonyu Kim, Taeyoun Kwon, Donghyuk Jung +1 more
CORTIS is a text-only adaptation framework that fine-tunes spoken language models for task-oriented voice agents using text-form task supervision.
This paper proposes Hypothesis-Driven Skill Optimization (HDSO), a train-free framework for improving action-oriented LLM agents with external skills while preserving their frozen inference endpoints.
This paper measures the impact of procedural skills on LLM agents, distinguishing between improvements and regressions, and identifies causes of regression.
Tianzhuo Yang, Zihan Shen, Zirui Mi, Zhaoyi Zhang +6 more
The paper introduces MiraBench, a new benchmark that evaluates the action-conditioned reliability of robotic world models, finding that visual fidelity is insufficient and that optimism bias is a perv…
This paper investigates various methods for encoding factored tasks, a compact planning representation, into propositional logic for use with SAT solvers, analyzing the impact of encoding choices and…
SCOPE introduces a data-free self-play framework that co-evolves a task-generating Challenger and a document-answering Solver, significantly improving open-ended performance on language models without…
One clear sentence describing what this paper does