Author

Rajeev Thakur

h-index 3 View on Semantic Scholar

We have 6 of 15 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.

Preprint Aug 2026

Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages

Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer. Such filtering assumes that a message likely to be correct is also worth keeping. Yet a wrong answer can contain a useful decomposition, constraint, or scientific principle. We test t...

Chih-Hsuan Yang, Anjir Ahmed Chowdhury, Cheng-Hau Yang et al. · 2 citations

#artificial intelligence Preprint Sep 2026

LAM: Efficient Lossy Agent Memory Framework With A Retrieval-Score Error Bound

LAM is proposed, a Lossy Agent Memory system with three components: a deterministic deduplication rule with a substitution bound on retrieval scores - a bound on score perturbation, not a certificate of unchanged ranking; a memory manager that preserves the cached prefix and overlaps compaction with inference; and a pe...

Bai-Xi Sun, Le Chen, Anjir Ahmed Chowdhury et al. · 0 citations

#natural language process... Preprint Aug 2026

What Confidence Routing Is Actually Doing: Auditing Routing, Calibration, and Commitment in Multi-Agent Deliberation

The transferable lesson is procedural: routing discrimination, probability calibration, and public commitment must be measured separately before raw confidence is used for deployment decisions.

Jingyan Jiang, Hui-Huo Zheng, Rajeev Thakur et al. · 0 citations

Preprint Aug 2026

FABRICA: Agentic CUDA-to-CSL Translation and Optimization for Wafer-Scale Systems

These results identify base-model capability, target knowledge, execution feedback, and same-target measurement as central to cross-architecture kernel generation as central to cross-architecture kernel generation.

Yuebo Luo, E. Huerta, Venkat Vishwanath et al. · 0 citations

#artificial intelligence Preprint Aug 2026

Measure Before You Manage: Evaluating Agent Working Memory in Coding Agents

This work focuses on semantic heterogeneity and studies how it should shape the management and evaluation of working memory in coding agents, finding that semantically different working-memory objects exhibit distinct retention and compression behavior.

Le Chen, Zi-Shen Wan, Bai-Xi Sun et al. · 1 citation

Review Aug 2026

LLMs Can Predict Failure Risk, But Struggle to Predict Which Collaboration Protocol Pays Off: Cost-Aware Protocol Routing Across Reasoning Tasks

Multi-agent large language model (LLM) systems can improve reasoning by spending more computation, but deployment requires deciding when extra collaboration is worth its cost, so confidence can support initial escalation, while protocol-specific cost-aware routing remains unresolved.

Chih-Hsuan Yang, Jingyan Jiang, Cheng-Hau Yang et al. · 0 citations