8 papers
StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments
Esakkivel Esakkiraja, Denis Akhiyarov, Vikas Yadav +4
We present StarHarness, a framework for evolving environment-specific agent harnesses while keeping model weights fixed. The evolved harness can include prompt and task framing, to…
Hybrid Retriever Evolution for Multimodal Document Reasoning Agents
Bohan Yao, Shruthan Radhakrishna, Vikas Yadav
Different retrievers, including lexical, semantic, and multimodal approaches, provide highly complementary strengths for multimodal document understanding, yet most systems combine…
Knowing When Not to Answer: Evaluating Abstention in Multimodal Reasoning Systems
Nishanth Madhusudhan, Vikas Yadav, Alexandre Lacoste
Effective abstention (EA), recognizing evidence insufficiency and refraining from answering, is critical for reliable multimodal systems. Yet existing evaluation paradigms for visi…
Grammar Search for Multi-Agent Systems
Mayank Singh, Vikas Yadav, Shiva Krishna Reddy Malay +4
Automatic search for Multi-Agent Systems has recently emerged as a key focus in agentic AI research. Several prior approaches have relied on LLM-based free-form search over the cod…
Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA
Rishabh Maheshwary, Masoud Hashemi, Khyati Mahajan +5
Iterative RAG for multi-hop question answering faces challenges with lengthy contexts and the buildup of irrelevant information. This hinders a model's capacity to process and reas…
DNR Bench: Benchmarking Over-Reasoning in Reasoning LLMs
Masoud Hashemi, Oluwanifemi Bamgbose, Sathwik Tejaswi Madhusudhan +3
Test-time scaling has significantly improved large language model performance, enabling deeper reasoning to solve complex problems. However, this increased reasoning capability als…