We have 7 of 18 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Results indicate that with zero curated data, OPT-Zero matches state-of-the-art data-dependent methods while exhibiting substantially stronger generalizability, establishing self-play training as a highly scalable paradigm for advancing LLM reasoning in modeling and solving optimization problems.
SOLID is proposed, a novel framework for self-improving OR language models without verified answers or external evaluators that improves solution accuracy for both general-purpose and OR-tuned models over outcome-only group-relative training.
This work introduces OR-Clarify, a benchmark for pre-formulation clarification and proposes Interactive Optimization (InterOPT), a two-stage framework that identifies unresolved formulation-critical gaps and uses them to guide whether to ask the next question or to stop.
A runtime gate for an LLM tool agent is usually cast as a filter. In a ReAct loop a rejected proposal is followed by another at the same state, so the gate is a search operator over the proposal stream whose admission criterion shapes which trajectories are reachable. We study post-violation recovery admission, where p...
Multi-turn agentic RL increasingly treats credit assignment as a targeting problem: given a terminal verifiable reward, per-turn methods localize credit onto the turns that mattered. We identify the structural quantity that predicts when this is the right move, the verifier information density V_d = k/C (the fraction o...
It is shown that conditioned on a candidate, a judge scores plausibility, not correctness, leaving false-positive basins a policy learns to exploit, and a falsifiable bound predicts which regimes are exposed.
Hard-constrained sequential decision systems have no certified way to spend the test-time compute of modern AI: executing the multi-step drafts of a learned policy or a frozen LLM forfeits the feasibility guarantee a trusted solver provides, while invoking the solver at every step forfeits the speed the AI offers. Cert...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
